mirror of
https://github.com/Gitlawb/openclaude.git
synced 2026-08-24 02:34:15 -05:00
main
53
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  anushka ✩andGitHub
|
294bd9a1df |
Add optional Sentry error reporting (env-driven, opt-in) (#2139)
* Add optional Sentry error reporting (env-driven, opt-in) * Fix Sentry init to use dynamic import instead of require (ESM compatibility) * Document SENTRY_DSN setup in advanced-setup docs * Disable Sentry default integrations; document runtime install requirement * Wire reportErrorToSentry into top-level error handlers; add sentry.test.ts |
||
 BogdanandGitHub
|
09eba26d30 |
feat(cost): support exact custom model pricing (#2131)
* feat(cost): support exact custom model pricing * fix(cost): address custom pricing review feedback |
||
|
BogdanandGitHub
|
c30578819e |
diagnostics(query): trace interruption causality (#2111)
* diagnostics(issue-1830): trace interruption causality * test(issue-1830): lock interruption ownership matrix * fix(codex): preserve stream deadline contract * fix(diagnostics): harden interruption trace lifecycle Refs #1830 * fix(diagnostics): harden interruption trace settlement Refs #1830 * fix(diagnostics): preserve interruption causality * fix(diagnostics): address interruption trace review * fix(diagnostics): preserve tracing observer contracts * fix(diagnostics): preserve interruption trace contracts * test(permissions): cover interactive hook interrupts |
||
 
|
95409464f3 |
feat(codex): move codexplan default to GPT-5.6 Sol (#2051)
* feat(codex): default codexplan to GPT-5.6 Sol
Preserve existing reasoning and routing behavior while updating the default model, labels, documentation, and focused coverage.
* test(codex): lock fallback and routing behavior
* make credential-step test self-contained
* fix(codex): default unset teammate fallback to GPT-5.6 Sol
The changes to the inert codex config keys are known to have no functional effect, but we updated them to ensure the defaults are correct and consistent across the table.
* fix codexplan gateway defaults after model resolution
* Revert "fix codexplan gateway defaults after model resolution"
This reverts commit
|
||
|
JATMNandGitHub
|
b0cbfe1100 |
fix(repl): make local interactive max-turns configurable (#2086)
* fix(repl): make interactive max-turns configurable Wire --max-turns into interactive sessionConfig and honor OPENCLAUDE_MAX_TURNS / CLAUDE_CODE_MAX_TURNS so long autonomous REPL sessions can raise the default 50-turn per-prompt cap (fixes #2079). * fix(repl): forward --max-turns on connect/ssh/remote launches sessionConfig covered the normal interactive paths; connect, SSH, assistant, and --remote built REPL props without spreading it, so the CLI override was dropped despite help advertising interactive support. * fix(repl): scope interactive max-turns to local query loops Remote-backed sessions bypass local query(), so forwarding --max-turns into those REPL props over-claimed enforcement. Clarify help/docs and match OPENCLAUDE_MAX_RETRIES precedence when OPENCLAUDE_MAX_TURNS is set but invalid. * feat(config): add interactive max turns under /config Expose replMaxTurns in the Config panel (50/100/200/500) and resolve it after CLI/env so local interactive sessions can raise the per-prompt cap without restarting. Resolve at query time so mid-session /config changes apply on the next prompt. * docs(repl): clarify invalid OPENCLAUDE_MAX_TURNS precedence Match the OPENCLAUDE_MAX_RETRIES contract: a set-but-invalid primary env var uses the default and does not fall through to legacy or /config. * fix(repl): address PR review on max-turns help and web version gate Share the --max-turns Commander description via an imported constant so help and tests stay in sync without breaking the CLI bundle, replace source-only help assertions with Commander behavior coverage, and add the published 0.27.0 entry so web verify-dist passes. * fix(repl): typecheck Commander maxTurns opts and warn on invalid env Avoid TS2339 on untyped Commander opts, log invalid OPENCLAUDE_MAX_TURNS like MAX_RETRIES, and clarify that /config shows the persisted preference. * fix(repl): warn when max turns is unlimited * fix(repl): scope unlimited-turn warning locally * fix(repl): preserve interactive turn caps across backgrounding * fix(repl): preserve turn caps when backgrounding * fix(repl): share turn budget across background handoff * fix(repl): reserve turns at provider dispatch * fix(repl): snapshot background handoff transcript * fix(tasks): avoid phantom background session task * fix(repl): preserve handoff lifecycle state * fix(repl): own pending background handoffs * test(tasks): isolate background session task storage * fix(repl): refresh background task title and test cleanup * test(repl): cover max-turn CLI dispatch paths * test(queue): cover prepend notification and priority * fix(repl): skip background handoff after foreground query throws Rebased onto main and gate Ctrl+B continuation on !didThrow so a faulted foreground turn cannot start a background session from partial state. * fix(repl): address PR review findings on notifications and handoff Dedupe background task notifications by embedded task id, gate background continuation on preflight veto, scope queue removal to main-thread notifications, and forward maxTurns through all launchRepl entry points. * fix(repl): resolve latest CodeRabbit inline review findings Dedupe claimed notification batches by task id, restore notifications on pre-registration abort, tighten test isolation, and replace remaining brittle source-text assertions with behavioral coverage. * fix(repl): keep notification restore active until provider dispatch Stop clearing notification ownership when preparation succeeds so pre-dispatch aborts can restore claimed queue items, and commit ownership once the provider starts. Add regression coverage for the abort path and headless max-turns zero. * test(repl): cover post-dispatch ownership and headless max-turns 0 Add regression tests for notification restore after provider dispatch commits ownership, and assert headless --max-turns 0 reaches query() without interactive resolution stripping the value. * fix(repl): restore only embeddable notifications on Ctrl+B handoff abort Track the deduped successor subset when restoring claimed main-thread task notifications so items already in the settled foreground transcript are not re-queued. Clarify that agent-scoped notifications intentionally stay on their owner drain path (issue #2079 scope is interactive turn caps only). * fix(repl): address review findings on background handoff Commit notification ownership when background sessions complete without provider dispatch, forward all task notifications on Ctrl+B again, and restore deferred max-turn cap attachments when continuation is cancelled. * fix(repl): guard deferred cap restore and skip remote turn limits Anchor deferred max-turn restoration to the handed-off transcript tail so a cancelled Ctrl+B handoff cannot attach the prior prompt's cap to a newer turn. Apply the interactive turn cap only in local sessions and align remote-session docs/help wording. * fix(repl): use messagesRef for deferred cap transcript anchor persistentMessages is block-scoped inside onQuery try; read the settled tail from messagesRef in finally so typecheck passes. * test: harden context fallback warning assertion after max-turns tests Scope the unknown-model context test to [context] warnings only so unrelated import-time debug logs do not fail CI, and clear turn env vars in both that test and replMaxTurnsProp setup to avoid cross-file pollution. * test: address PR review findings on headless max-turns boundary Add a runHeadless-to-ask regression that asserts maxTurns 0 is forwarded through the headless print path, and restore OPENCLAUDE_MAX_TURNS env vars in context.test.ts after the unknown-model fallback test mutates them. * test: tidy headless max-turns boundary test and env isolation Mock headless stdout so runHeadless completes cleanly without leaking output, restore spies in finally, and centralize turn-env cleanup in context.test beforeEach. * fix: address PR review findings for max-turns background handoff Separate model-request lifecycle from provider dispatch acceptance so interruption correction arms before async prep, notification ownership commits only after dispatch, deferred turn caps restore on every abort path, and foreground work stays blocked while handoff preparation runs. |
||
 0xfandomandGitHub
|
3925f2791c |
feat(auth): opt-in loopback proxy hosts that keep subscription (OAuth) auth (#2050)
* feat(auth): opt-in loopback proxy hosts that keep OAuth first-party Pointing ANTHROPIC_BASE_URL at any host other than api.anthropic.com switches the client to API-key mode, dropping a signed-in subscription session. That blocks running the CLI through a local transparent proxy (compression, inspection, caching) that forwards auth headers to Anthropic unchanged. Add ANTHROPIC_FIRST_PARTY_PROXY_HOSTS: a comma-separated host[:port] allowlist that extends first-party detection. It is honored only when the base URL points at a loopback host, and only loopback entries are considered -- both checks are redundant by design so a misconfigured non-loopback entry can never widen first-party status to an off-machine host. Default behavior is unchanged. Closes #2016 * docs(auth): document ANTHROPIC_FIRST_PARTY_PROXY_HOSTS * fix(auth): harden loopback proxy allowlist matching Normalize the base URL port to its scheme default (80/443) before comparing an explicit allowlist port, so a `127.0.0.1:80` entry matches `http://127.0.0.1`. Reject embedded credentials and non-http(s) schemes up front so an OAuth session is never attached to a URL carrying userinfo or a non-proxy scheme. |
||
|
|
3808d19da4 |
fix(api): enforce API_TIMEOUT_MS for OpenAI-compatible headers (#1940)
* fix(api): enforce API_TIMEOUT_MS for OpenAI-compatible headers * test(api): cover Copilot responses fallback deadlines * fix(api): redact secrets in timeout URL paths * fix(api): harden Copilot response deadlines * fix(api): prevent header-timeout request replay * fix(api): harden timeout cleanup and redaction * fix(api): redact encoded transport credentials * fix(api): harden deadline retries and URL redaction * fix(api): preserve aborted fetch reasons * fix(api): preserve caller abort reasons * test(api): clear caller abort timer * docs(api): clarify API_TIMEOUT_MS transport scope * docs(api): explain timeout env loading * fix(api): reset deadline for proxy retries * fix(api): type deadline fetch adapter * fix(api): honor abort cleanup and request signals * fix(api): do not block proxy retries on body cancellation --------- Co-authored-by: jatmn <the@jat.mn> |
||
|
JATMNandGitHub
|
46e80568be |
fix(provider): support custom Anthropic bearer auth (#1929)
* fix(provider): support custom Anthropic bearer auth * feat(provider): add custom Anthropic profile flow * fix(provider): restore custom Anthropic tokens on startup * fix(provider): preserve custom Anthropic env setup * fix(provider): clear stale custom Anthropic tokens * fix(provider): preserve custom Anthropic API-key env setup * fix(provider): cover custom Anthropic auth routing * test(api): isolate custom Anthropic client routing * test(api): cache-bust client provider imports * feat(provider): clarify custom provider presets * fix(provider): address custom Anthropic review feedback * fix(provider): preserve custom Anthropic headers * fix(provider): require custom Anthropic token * fix(provider): isolate custom Anthropic credentials * fix(provider): guard custom Anthropic setup * fix(provider): complete custom Anthropic integration * fix(provider): classify custom Anthropic proxies * fix(provider): gate proxy cache extensions * fix(provider): preserve custom Anthropic isolation * fix(provider): retain direct proxy model option * fix(provider): honor custom endpoint boundaries * fix(provider): keep proxy credentials local * fix(provider): disable proxy fast mode * fix(provider): preserve first-party route identity * fix(provider): isolate custom Anthropic endpoints * fix(provider): gate remaining first-party features * fix(provider): isolate custom Anthropic proxy features * test(web-search): make Brave timeout mock abort-aware * fix(provider): address custom Anthropic review feedback * test(provider): cover first-party beta gates * fix(provider): complete custom Anthropic isolation * fix(provider): complete custom Anthropic routing * fix(provider): address custom Anthropic review followups * fix(provider): close custom Anthropic review gaps * test(provider): keep custom Anthropic mock helpers isolated * test(provider): isolate model options gateway mocks * fix(provider): stabilize custom Anthropic model option display * fix(provider): address remaining review threads * fix(provider): synchronize active profile persistence * fix(provider): preserve custom Anthropic API key auth * fix(provider): avoid forwarding inherited Anthropic keys * fix(provider): guard custom auth selection * fix(provider): require first-party Anthropic port * test(web-search): avoid duplicate shared lock * fix(provider): resolve remaining review findings * fix(provider): harden custom Anthropic routing * fix(provider): simplify Anthropic thinking gate * fix(provider): preserve custom proxy routing and secret permissions * fix(mcp): isolate Claude.ai config cache by provider * fix(model): keep custom endpoints out of first-party UX * fix(provider): scope Opus off switch to Anthropic * fix(provider): disable tool search for custom proxies * fix(provider): close custom Anthropic review gaps * fix(provider): reject Anthropic staging custom profiles * fix(webfetch): classify custom Anthropic endpoints * fix(provider): block bearer auth at Anthropic origin * fix(provider): keep custom auth off staging OAuth * test(provider): strengthen auth regression coverage |
||
|
a32781537f |
fix(query): bound per-turn latency growth in long REPL sessions (#1949) (#1952)
* fix(query): bound per-turn latency growth in long REPL sessions (#1949) Addresses the progressive latency regression where consecutive prompts in a single session grow non-linearly (2nd prompt ~10s, 3rd 10+ min) due to unbounded message accumulation with no proactive compaction and no per-prompt turn cap on the main thread. - Cap the interactive REPL main thread at 50 turns per prompt (DEFAULT_REPL_MAX_TURNS). Headless/print mode and the SDK are unchanged (--max-turns flag / SDK callers still control it), preserving the SDK API contract. - Default maxMessagesCompactionThreshold to '200' so message-count compaction runs well before the context window fills, instead of 'off'. - Lower the auto-compact threshold buffer from 13k -> 30k so compaction fires earlier with less accumulated history. The effective-context floor buffer is kept at 13k and getAutoCompactThreshold() falls back to it for small-context models, so the threshold can never go negative (no #635 regression). Test updates: isolate the hard-cap override test from the new 200-message default, and correct an outdated constant reference in the autoCompact test. Co-Authored-By: Claude <noreply@anthropic.com> * fix(query): repair REPL latency guard * fix(query): cover resume and default guard paths * fix(query): enforce cap across interactive paths * docs(compaction): clarify disabled message limits * fix(query): retain explicit message thresholds * fix(query): enforce explicit threshold recovery * fix(query): honor legacy active-message limit * fix(doctor): report effective message compaction limit * fix(config): share message threshold validation * test(doctor): cover disabled message compaction * fix(compact): preserve latency guard coverage * test(repl): exercise turn cap defaults * fix(compact): honor disabled default message guard * fix(swarm): honor disabled auto compaction --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
0xfandomandGitHub
|
eeed68f4fd |
feat(provider): add Cloudflare Workers AI integration (#1100) (#1178)
* feat(provider): add Cloudflare Workers AI integration
Adds Cloudflare Workers AI as a first-class OpenAI-compatible provider
preset, modeled on the Venice / Xiaomi MiMo descriptors.
- New `src/integrations/vendors/cloudflare.ts` descriptor:
- `classification: 'openai-compatible'`
- Default base URL with literal `<ACCOUNT_ID>` placeholder — users
substitute via `/provider` baseUrl edit, same shape as the Azure
OpenAI example already in `docs/advanced-setup.md`
- `CLOUDFLARE_API_TOKEN` env, with `OPENAI_API_KEY` as fallback
- `removeBodyFields: ['store']` since Workers AI rejects unknown
OpenAI body fields (mirrors Mistral / Gemini / Cerebras strip)
- Static catalog with current Workers AI chat models
(`@cf/meta/llama-3.3-70b-instruct-fp8-fast`,
`@cf/meta/llama-3.1-8b-instruct`,
`@cf/deepseek-ai/deepseek-r1-distill-qwen-32b`,
`@cf/qwen/qwen2.5-coder-32b-instruct`)
- Validation routing on `api.cloudflare.com` /
`gateway.ai.cloudflare.com` hosts so an env-pasted URL maps back
to the preset
- Env mirror sites in `src/utils/providerProfiles.ts`: mirror api key
into `CLOUDFLARE_API_TOKEN` when baseUrl contains a Cloudflare host
(3 sites: same-env check, openAIProfileEnv build, applyEnv).
- `CLOUDFLARE_API_TOKEN` added to `PROFILE_ENV_KEYS` / `SECRET_ENV_KEYS` /
`ProfileEnv` / `SecretValueSource` in `src/utils/providerProfile.ts`
so the profile-clean and secret-redact paths know about it.
- `src/utils/providerFlag.ts` `--provider <name>` startup flag now
detects a Cloudflare profile from `OPENAI_API_KEY ===
CLOUDFLARE_API_TOKEN` (mirrors how the other host-key mirrors are
reverse-mapped to their preset id).
- `bun run scripts/generate-integrations-artifacts.ts` regenerated
`integrationArtifacts.generated.ts` to include the cloudflare preset
+ route + vendor.
- Tests: `compatibility.test.ts` PRESETS list, new
`buildProfileSaveMessage` Cloudflare case in `provider.test.tsx`,
new `applyProviderProfileToProcessEnv` Cloudflare case in
`providerProfiles.test.ts`.
- Docs: README providers table row + `docs/advanced-setup.md` section
matching the MiMo / Mistral entries.
- Dedicated AI Gateway integration with `gateway_id` URL templating.
Today users can still paste a full Gateway URL into `OPENAI_BASE_URL`
and the preset's `matchBaseUrlHosts` picks `gateway.ai.cloudflare.com`
up.
- Dynamic `/models` discovery on the Groq #1143 / `mapModel` pattern —
Cloudflare's `/v1/models` returns the runnable model list and the
hybrid catalog path drops in cleanly. Left as a separate PR so this
one stays a focused preset add.
Closes #1100
* fix(cloudflare): narrow route matching to api.cloudflare.com host
`gateway.ai.cloudflare.com` is the shared host for *all* Cloudflare AI
Gateway routes (Workers AI, Anthropic, OpenAI, etc.), so matching it to
the Workers AI preset applied Workers-AI runtime metadata and
credential precedence (CLOUDFLARE_API_TOKEN before OPENAI_API_KEY, body
'store' strip, max_tokens field) to other providers' Gateway URLs.
Drop the shared host from the match list; a dedicated AI Gateway
integration with path-aware routing is the right follow-up.
Refs #1100.
* fix(provider-manager): keep Codex OAuth after DeepSeek when cloudflare added
The picker hardcoded `options.splice(7, 0, …)` to drop the Codex OAuth
entry right after DeepSeek. Adding cloudflare to ORDERED_PROVIDER_PRESETS
bumped DeepSeek to index 7, so the splice now lands Codex OAuth *before*
DeepSeek and breaks the test fixture that drives navigateToPreset by
keypress count.
Switch to a dynamic `findIndex('deepseek') + 1` lookup so any future
preset inserted between Bankr and DeepSeek keeps the established
ordering. Fixture updated to mirror the new picker order.
Caught by CI on 12b3ff… smoke-and-tests: 8 ProviderManager tests
timing out because navigateToPreset overshot/undershot the target.
* fix(cloudflare): exclude the shared AI Gateway host from Cloudflare routing
The profile env/alignment/startup paths mirrored CLOUDFLARE_API_TOKEN whenever
the profile URL merely contained 'gateway.ai.cloudflare.com'. That host is the
shared AI Gateway for all Cloudflare AI routes (Workers AI, OpenAI, Anthropic,
...), so a profile retargeted to /openai or /anthropic Gateway URLs was wrongly
tied to the Cloudflare route and credential precedence.
Add isCloudflareBaseUrl (hostname === api.cloudflare.com, matching the Workers
AI host and the descriptor's matchBaseUrlHosts) and route all three sites
through it, consistent with isXaiBaseUrl/isFireworksBaseUrl. Also restore
CLOUDFLARE_API_TOKEN in the provider profile test cleanup keys.
* fix(cloudflare): don't seed the placeholder base URL from the CLI shortcut
`openclaude --provider cloudflare` fell through the generic OpenAI-compatible
branch and applied the descriptor default base URL verbatim — including the
unresolved `<ACCOUNT_ID>` placeholder — leaving the shortcut 'configured' with
an endpoint that cannot serve a request. Skip seeding any base URL that still
contains a `<...>` placeholder, so the user must supply a real account-scoped
URL (OPENAI_BASE_URL / `/provider` edit) first, matching how the wizard treats
placeholder endpoints.
* test(cloudflare): assert exact null fallback for AI Gateway routes
The shared AI Gateway URL assertions used `.not.toBe('cloudflare')`, which
would also pass for any other non-cloudflare return value. The intended
fallback is null, so assert `.toBe(null)` to lock the regression boundary.
* fix(cloudflare): gate profile token mirroring on base URL host only
applyProviderProfileToProcessEnv mirrored CLOUDFLARE_API_TOKEN whenever
route.routeId === 'cloudflare'. route comes from the saved profile.provider,
so that disjunct is always true for a cloudflare profile, including one
retargeted to the shared gateway.ai.cloudflare.com AI Gateway host. The
sibling sites (isProcessEnvAlignedWithProfile, buildOpenAICompatibleStartupEnv)
already key on isCloudflareBaseUrl only; align this site with them so a
shared-gateway profile no longer leaks the token or stays pinned to the
cloudflare route. Add a regression test for the gateway.ai.cloudflare.com case.
* chore(integrations): regenerate artifacts for the Cloudflare vendor
The rebase took main's generated artifacts at the conflict; regenerate so the
Cloudflare vendor descriptor is registered in VENDOR_DESCRIPTORS and the
manifest alongside the providers main added.
* fix(cloudflare): mirror CLOUDFLARE_API_TOKEN into the OpenAI-compatible auth path
The --provider cloudflare shortcut fell through to the generic
OpenAI-compatible default branch and never copied CLOUDFLARE_API_TOKEN
into OPENAI_API_KEY, so a user who only set the token sent an
unauthenticated request. Add a dedicated cloudflare case that mirrors the
token (and clears a stale generic key when absent), keeping the
placeholder-URL skip.
buildOpenAICompatibleStartupEnv also returned from its strict-env branch
before the fallback CLOUDFLARE_API_TOKEN mirror, so a keyed Cloudflare
profile persisted a startup env that omitted the token and re-detected
inconsistently after relaunch. Mirror it in the strict branch alongside
nearai/fireworks. Add regression coverage for both paths.
* fix(cloudflare): gate token mirroring on a real Cloudflare endpoint
The cloudflare shortcut copied CLOUDFLARE_API_TOKEN into the generic
OPENAI_API_KEY unconditionally. The descriptor default carries an
unresolved `<ACCOUNT_ID>` placeholder and is never seeded, so with
OPENAI_BASE_URL unset (or still pointing at a previous OpenAI-compatible
provider) the token would be attached to the wrong host. Gate the mirror
on isCloudflareBaseUrl(getConfiguredOpenAIBaseUrl()) — only seed
OPENAI_API_KEY once the configured base URL resolves to
api.cloudflare.com, otherwise fail fast and leave it unset. Add
regression coverage for the unconfigured, stale-host, and AI-Gateway-host
cases.
* fix(cloudflare): reject placeholder URL and keep the OPENAI_API_KEY fallback
The token mirror keyed on the api.cloudflare.com host only, so the literal
<ACCOUNT_ID> placeholder URL (same host) passed the gate and copied the
token onto a non-working endpoint. It also deleted any generic
OPENAI_API_KEY when no token was set, breaking the documented
compatibility fallback for users authenticating a real Workers AI URL with
OPENAI_API_KEY. Mirror only on a real (non-placeholder) Cloudflare
endpoint, and preserve an existing generic key there when no dedicated
token is present.
Refs #1100
* refactor(cloudflare): model Workers AI as a gateway, not a vendor
Cloudflare Workers AI is a hosted OpenAI-compatible inference endpoint
reached over the shared openai transport, so it belongs with the gateway
providers (atlas-cloud, groq, together, ...) rather than the transport
vendors. Move it to gateways/cloudflare.ts via defineGateway (category
hosted, vendorId openai), regenerate the integration artifacts, and
allowlist its provider-specific @cf/* catalog ids in the gateway
descriptor check (no shared cross-provider descriptor exists, same as
azure-deployment).
Refs #1100
* fix(cloudflare): key Workers AI detection on the account path, not the host
api.cloudflare.com also serves the general Cloudflare REST API, so matching the
whole host treated unrelated URLs (e.g. /client/v4/user/tokens/verify) as the
Workers AI route and mirrored CLOUDFLARE_API_TOKEN into OPENAI_API_KEY for them.
isCloudflareBaseUrl now requires the Workers AI path
/client/v4/accounts/<account_id>/ai/v1 with a real (non-placeholder) account id,
and resolveRouteIdFromBaseUrl guards its cloudflare hostname match through the
same predicate. Both route detection and token/profile mirroring key on the
actual Workers AI endpoint.
Adds same-host negative regressions (general REST path is not routed and does
not mirror the token; unresolved <ACCOUNT_ID> placeholder is excluded) and
asserts the Cloudflare Workers AI preset appears in the first-run picker.
* fix(cloudflare): honor the Workers AI path boundary in the profile-provider fallback
resolveActiveRouteIdFromEnv returned the saved active-profile provider's route
id before consulting its base URL. For a `cloudflare` profile that had been
retargeted to a non-Workers URL — the shared AI Gateway host, or a general
api.cloudflare.com REST path — this still resolved as `cloudflare`, so the
Workers AI shim config (removeBodyFields: ['store'], Cloudflare model metadata)
and CLOUDFLARE_API_TOKEN mirroring were applied to a generic endpoint, even
though resolveRouteIdFromBaseUrl already excludes those URLs.
Gate the profile-provider shortcut through profileRouteHonorsBaseUrlBoundary,
which requires the path-aware isCloudflareBaseUrl for the cloudflare route (all
other routes are host-scoped by resolveProfileRoute and unaffected). A retargeted
profile now falls through to the generic openai/custom resolution; a genuine
Workers AI profile base URL still resolves as cloudflare.
Adds regressions for both retarget cases (gateway host + REST path) and the
positive Workers AI profile case.
* fix(cloudflare): require HTTPS and honor the Workers AI path in validation
isCloudflareBaseUrl accepted any scheme, so http://api.cloudflare.com/
client/v4/accounts/<id>/ai/v1 resolved as the cloudflare route and mirrored
CLOUDFLARE_API_TOKEN into OPENAI_API_KEY over cleartext. Require url.protocol
=== 'https:'.
Startup validation selected the Cloudflare target on host match alone, so a
non-Workers path like /client/v4/user/tokens/verify demanded Workers AI auth
instead of falling back to generic OpenAI validation. Gate the cloudflare
target on isCloudflareBaseUrl(request.baseUrl), mirroring the runtime route
resolver's path boundary.
* test(cloudflare): lock non-Workers path token boundary; fix stale host-only comments
The apply/persist paths already gate CLOUDFLARE_API_TOKEN mirroring on the
isCloudflareBaseUrl path predicate, but had no coverage for a same-host
non-Workers path (api.cloudflare.com/client/v4/user/tokens/verify) and the
comments beside the mirroring sites still described a host-only boundary.
Add negative apply and persist regressions asserting the token is not mirrored
or persisted for that non-Workers URL, and update the comments to describe the
real Workers AI path predicate instead of host-only matching.
* fix(cloudflare): fall back to a generic route for retargeted profiles
resolveProfileCapabilityRouteId returned the cloudflare capability route id for
any saved cloudflare profile whose base URL no longer resolves — including one
retargeted to gateway.ai.cloudflare.com or another OpenAI-compatible host. That
stripped generic capabilities (apiFormat, custom auth/request headers) from
profile sanitize/apply even though the runtime resolver runs such a profile as
a generic OpenAI-compatible route. Mirror the same isCloudflareBaseUrl boundary:
keep the cloudflare route only for the real Workers AI URL (or the unset
descriptor default) and fall back to 'custom' otherwise. Regression asserts a
retargeted cloudflare profile preserves OPENAI_API_FORMAT.
* test(cloudflare): assert retargeted profile resolves to the custom route
Pin both resolveActiveRouteIdFromEnv assertions for a retargeted cloudflare
profile to .toBe('custom') instead of .not.toBe('cloudflare'), so the test
locks the intended generic OpenAI-compatible fallback rather than merely
excluding the cloudflare route.
|
||
|
JATMNandGitHub
|
e086e8c35a |
fix(safety): relax over-restrictive safety checks for benign coding tasks (#1897)
* fix(safety): relax over-restrictive safety checks for benign coding tasks (Fixes #1616) Issue #1616 reports refusals for routine, benign coding tasks. Two layers caused this: 1. Model-level over-refusal: CYBER_RISK_INSTRUCTION and the 'ask before acting' guidance biased the model toward refusing normal work. Reworded to explicitly permit ordinary engineering tasks and dual-use/security-adjacent work in authorized contexts, and to ask a clarifying question rather than refuse when intent is ambiguous. 2. Application-level heuristics that become hard blocks in auto/YOLO/headless mode: the bash command-injection check, the broad DANGEROUS_FILES/DANGEROUS_DIRECTORIES auto-edit guard, and the auto-mode stripping of ordinary interpreter allow-rules (Bash(python:*), npm run:*, etc.). Added an OPENCLAUDE_SAFETY_LEVEL knob (strict|balanced|permissive, default balanced). In 'permissive' the application-level heuristics above are relaxed while genuine Windows-path/symlink guards remain active. Default behavior is unchanged. Validation: - bun run typecheck: clean - bun run build: succeeds - bun test safetyLevel.test.ts, bashSecurity.safety.test.ts: pass - bashSecurity.test.ts, filesystem.test.ts, permissionSetup.test.ts, security-hardening.test.ts: pass (no regressions) * fix(safety): narrow permissive safety relaxations * fix(safety): address review follow-ups * fix(safety): address additional review findings * refactor(permissions): share rule normalization |
||
|
0xfandomandGitHub
|
06e0ae6e0b |
feat(settings): per-model context_window and max_output_tokens overrides (#1234)
* feat(settings): per-model context_window and max_output_tokens overrides
Adds a `modelLimits` settings.json map so users can declare context window
and max output tokens for OpenAI-compatible models that are not in the
built-in catalog. Resolution order is env var → settings → catalog, so the
existing CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS / _MAX_OUTPUT_TOKENS env vars
keep priority. Keys are matched exactly, then by prefix, with optional
"<host>:<model>" host-qualified forms.
Example:
"modelLimits": {
"qwen3.6-plus": { "contextWindow": 1048576, "maxOutputTokens": 32768 }
}
Closes #478
* fix(model-limits): apply settings overrides in resolveModelRuntimeLimits
The settings.json `modelLimits` fallback was only wired into the scalar
getOpenAIContextWindow / getOpenAIMaxOutputTokens helpers. The runtime
resolution path (resolveModelRuntimeLimits) instead consumes the *Matches
variants, which only returned env-var matches — so a configured modelLimits
override never reached the model whose limits are actually resolved at
runtime, contrary to the documented env → settings → catalog order.
Fold the settings lookup into getOpenAIContextWindowMatches /
getOpenAIMaxOutputTokenMatches as a dedicated `settings` field, and insert it
between the exact env override and the built-in catalog in
resolveModelRuntimeLimits. Declare `modelLimits` on GlobalConfig so the lookup
is typed. Add an integration test that drives resolveModelRuntimeLimits and
asserts settings resolve for exact, host-qualified and prefix keys, and that an
env override still wins.
* fix(model-limits): resolve modelLimits from settings.json, not global config
readSettingsLimits read getGlobalConfig().modelLimits, which is ~/.openclaude.json
— a different file from the settings.json the feature is documented and schema'd
for (SettingsSchema in settings/types.ts). A user adding modelLimits to
settings.json saw no effect. Read it from getInitialSettings() (the merged
settings snapshot, session-cached) instead, and drop the now-unused modelLimits
field from GlobalConfig so the override lives in one place. Rewire both test
suites to a gated-passthrough getInitialSettings mock.
* test(model-limits): capture real settings module at load, not in beforeEach
The settings modelLimits suites re-imported the real settings module with
a cold dynamic import inside beforeEach. That import sat right at Bun's
default 5s hook timeout and intermittently failed the first test. Capture
the genuine module once via a top-level query-string-busted static import
so the cost moves to module load (no hook timeout) and the gated
passthrough still bypasses other suites' settings.js mocks. Also correct
the integration-test comment to name the helpers the runtime path
actually calls (getOpenAIContextWindowMatches / getOpenAIMaxOutputTokenMatches).
* fix(model-limits): keep env-prefix override above settings in runtime resolver
resolveModelRuntimeLimits ordered the settings `modelLimits` value above
the env-prefix match, so a broad env-prefix override (e.g.
`{"my-custom":N}`) was silently overtaken by a more specific settings
entry (`my-custom-deployment`). The scalar getOpenAIContextWindow treats
env (exact ?? prefix) as strictly higher priority than settings; mirror
that in the runtime resolver: env.exact, then env.prefix, then settings,
then catalog/cache/descriptor. Regression covers both contextWindow and
maxOutputTokens.
* docs(model-limits): document the settings.json modelLimits override
Add a user-facing section near the env-var overrides covering the
modelLimits map, JSON shape, exact/prefix/host-qualified key matching, and
the env > settings > catalog > descriptor precedence.
* fix(model-limits): keep catalog above env-prefix in runtime precedence
The previous reorder put the env-prefix match above the catalog value,
which broke the existing invariant that a `:cloud` catalog variant takes
its known catalog limit rather than inheriting a broad base-model env
prefix (deepseek-v4-pro:cloud regressed to 262144). Correct order:
exact env -> catalog/cache -> env prefix -> settings -> descriptor. This
still keeps settings strictly below env-prefix (the original drift fix)
while preserving catalog precedence over prefix. Docs precedence updated
to match.
* docs(advanced-setup): document CLAUDE_CODE_OPENAI_MAX_OUTPUT_TOKENS env var
The modelLimits section referenced the max-output env var but the
Environment Variables table only listed the context-window one, leaving
output-only configuration undocumented. Add the matching table row.
Refs #478
* docs(model): align openaiContextWindows precedence comments with the resolver
The module header and the OpenALimitOverrideMatches.settings comment claimed a
resolution order of "env → settings → catalog", which contradicts
resolveModelRuntimeLimits (exact env → catalog/discovery cache → prefix env →
settings modelLimits → descriptor default). Since this module only produces the
override candidates and does not own the precedence, narrow the comments to say
so and point at runtimeMetadata.ts as the authoritative chain, so this
precedence-sensitive code isn't misread when touched again.
* fix(model): rank host-qualified modelLimits keys above bare model keys
lookupByModel grouped all exact matches (host-qualified and bare) ahead of all
prefix matches, so a bare exact key like `qwen3.6-plus` beat a host-qualified
prefix like `openrouter.ai:qwen3`. That defeated the advertised per-endpoint
disambiguation for versioned model families. A host-qualified key is strictly
more specific than a bare one, so rank both host-qualified forms (exact and
prefix) in the high-priority tier ahead of the bare exact match, leaving only
the bare prefix in the low-priority tier.
* fix(model): keep an exact modelLimits key ahead of any host-qualified prefix
The previous commit ranked host-qualified PREFIX matches above bare exact
matches, which broke the deliberate precedence in context.test.ts: an exact
`gpt-4o` limit was overridden by an unrelated `api.foo.com:gpt-4` prefix that
only matches a shorter, different model name.
Restore the tiering so an exact match (host-qualified or bare) always beats a
prefix, and a host-qualified key beats a bare key WITHIN the same match kind.
The supported way to set a different limit for the same model per endpoint is a
host-qualified EXACT key. Narrow the regression + comment to that behavior.
* docs(model): align modelLimits matching wording with exact-over-prefix rule
Narrow the advanced-setup wording so a host-qualified key only wins over a bare
key within the same match kind (a bare exact key still beats a host-qualified
prefix), matching lookupByModel's exact ?? prefix behavior; per-endpoint limits
for the same model need host-qualified exact keys. Also note modelLimits as part
of the documented user-override layer in the integration add-model and
common-pitfalls guides.
* docs(model): clarify modelLimits host-port key and catalog/cache precedence
Spell out that the host-qualified key uses new URL(baseUrl).host — including the
port when present (localhost:4000:my-model, not localhost:my-model) — and split
the precedence line so the built-in catalog is shown as checked before the
discovery-cache value, matching resolveModelRuntimeLimits.
|
||
|
0xfandomandGitHub
|
db01038d5c |
feat(model-picker): surface inactive provider profiles in /model (#1119 piece 2) (#1164)
* feat(model-picker): surface inactive provider profiles in /model When a user configures multiple providerProfiles (Kimi + Z.AI + OpenRouter + SambaNova in the #1119 repro, but the pattern fits any multi-provider setup), switching the main session between them currently requires round-tripping through /provider — /model only shows the active profile's models. Make /model the single switcher: - ModelOption gains an optional `switchToProfileId`. Existing options leave it unset and behave exactly as today. - `getInactiveProviderProfileOptions` enumerates every configured profile that isn't the active one and emits a picker entry per model, labelled `<model> · <profile.name>` so the user can see the choice changes providers, not just models. - Each option's `value` is encoded with `__switch_profile__:<id>:<model>` so the picker's plain-string `value` channel stays the source of truth and same-named models under different base URLs (`gpt-4o` on multiple OpenAI-compatible endpoints) stay disambiguated. - /model's handleSelect detects the prefix, calls `setActiveProviderProfile` (same path /provider uses — applies env, persists active profile, refreshes startup file), then sets `mainLoopModel` to the bare model string. Only surfaces inactive options when `CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED` is set, so users who haven't opted into the multi-profile workflow at all don't see the affordance. Tests cover round-trip encoding (including OpenRouter-style colon-bearing model strings), the active-filter, the multi-model explosion, and that `getModelOptions()` 3P path includes the inactive options only when the profile env is applied. Combined invocation with the rest of `src/utils/model/` + `src/commands/model/` + `src/utils/providerProfiles.test.ts` runs clean to guard against mock-leak (per the 2026-04-30 lesson — spreads `import * as actual` for every `mock.module` factory). Refs #1119 * fix(model-picker): run fast-mode cleanup on cross-profile switch The new switch-profile branch returned before reaching the fast-mode reconciliation, so a user with fastMode latched on Anthropic Opus could switch to an OpenAI profile and silently keep fastMode on even though the new model can't support it. Extract the cleanup into a pure helper `reconcileFastModeForSwitch` and call it from both branches. Refs #1119. * fix(model-picker): decode cross-profile values before effort/display lookup Inactive-profile entries encode the picker value as `__switch_profile__:<profileId>:<model>`, but `resolveOptionModel` forwarded the raw string straight to `parseUserSpecifiedModel`. For a reasoning-capable cross-profile entry such as `gpt-5.4`, `modelSupportsEffort()` then saw the prefixed string and reported "Effort not supported", and `handleSelect` dropped the toggled effort even when the underlying model accepts it. Run `parseSwitchProfileValue` first; when it matches, hand the bare target model to `parseUserSpecifiedModel` so effort capability, default-effort lookup, and display-name resolution all key off the real model id. * fix(model-picker): include inactive profiles on local OpenAI-compatible scope The inactive-profile compute lived after the `getAdditionalModelOptionsCacheScope()?.startsWith('openai:')` early return, so users with a local OpenAI-compatible profile active (Ollama, lm-studio, any localhost endpoint) never saw the cross-profile switcher in `/model`. They still had to round-trip through `/provider` to change profile. Hoist `profileEnvApplied`, the active-profile lookup, and `getInactiveProviderProfileOptions(activeProfileId)` above the early return, and append `inactiveProfileOptions` to the local-OpenAI branch return value. Other branches (Claude.AI, MiMo, MiniMax, ant) were already either irrelevant or have their own gating. Test: new regression in modelOptions.crossProfile.test.ts pins `getAdditionalModelOptionsCacheScope` to an `openai:` value and confirms the inactive profile still surfaces with a parseable `__switch_profile__` value. * fix(model-picker): apply the allowlist to the decoded cross-profile model filterModelOptionsByAllowlist evaluated cross-profile options by their encoded __switch_profile__:<id>:<model> value, so an availableModels allowlist that permits the bare target (e.g. glm-5.1) dropped every inactive-profile entry. Check the allowlist against parseSwitchProfileValue(value)?.model ?? value, and cover both the allowed and denied cases. * fix(model-picker): only surface cross-profile switch options on the /model path The inactive-profile entries come from the shared getModelOptions() list, but only the /model command's onSelect decodes __switch_profile__ values and activates the target profile. The prompt hotkey and Settings pickers wrote the encoded value straight to mainLoopModel, sending an invalid model string. Gate these options behind a new allowProfileSwitch prop that only the /model command sets; inline pickers no longer surface an option they cannot honor. Also apply the org allowlist to the decoded target model in the /model select handler. * test(model-picker): drop flaky cross-profile allowlist case The decoded-allowlist assertion drove the org allowlist through the shared session settings cache, which is racy across bun's single-process run and could leak availableModels into sibling suites (the providerConfig cache-scope tests went red in CI). The decode itself is a one-line guard already exercised by the parseSwitchProfileValue round-trip coverage, so remove the unreliable case rather than ship CI flake. Also snapshot the real provider/auth modules before mocking so each harness call rebuilds its mock from a clean base instead of a previous test's overrides (bun live-repoints the imported namespace to the active mock). * test(model-picker): stop cross-profile mocks leaking into provider suites The cross-profile tests mock.module'd ../providerProfiles, ./providers, ../auth and ../../services/api/providerConfig per test. bun's mock.module is process-wide and mock.restore() does not undo it, so these persisted into later files — most damagingly the providerConfig mock, which replaced the module with a single-function stub and stripped resolveProviderRequest / getAdditionalModelOptionsCacheScope from providerConfig.local's suite (now adjacent after the rebase onto #1706). Install each mock once at module load, keep the full export surface, and gate the overrides on module-level flags cleared in beforeEach/afterEach so the persisted mocks are transparent passthroughs for every other suite. Same pattern as the cross-spawn / install-surfaces leak fixes. * fix(model): reconcile fast mode before activating the switched profile In the cross-profile /model switch path, reconcileFastModeForSwitch ran after setActiveProviderProfile. The reconciler gates on isFastModeEnabled(), which reads the *active* provider — so once the target profile is activated it reflects the new (fast-mode-less) provider and short-circuits to 'unchanged', leaving fastMode latched on for a model that can't use it. Compute the reconciliation before activating the profile, so it evaluates against the source provider and correctly returns 'off' for an unsupported target. Add a command-level regression test that drives handleSelect with a __switch_profile__ value while setActiveProviderProfile flips the fast-mode state, and asserts fastMode is set to false (it fails if the call order regresses). * fix(model): re-check fast mode after activating a switched profile The pre-activation reconcile gates on the source provider, so its 'on' result is stale when the target provider cannot run fast mode even though the target model name passes the source-side support check (e.g. a third-party shim exposing a claude-opus-* model). Re-evaluate isFastModeEnabled / supported / available after setActiveProviderProfile and force fastMode off when it is no longer genuinely supported. Add a command-level regression test for that path and wrap the cross-profile test cleanup in try/finally so a failing assertion still unmounts the Ink instance (jatmn review, #1119). * test(model-picker): cover cross-profile allowlist with isolated settings Re-add the regression dropped in 06a0c80: filterModelOptionsByAllowlist must evaluate the allowlist against the decoded target model, not the encoded __switch_profile__ wrapper. Uses this suite's per-test settings cache (reset in afterEach) instead of the shared cache that made the earlier version flaky (jatmn review, #1119). * test(model-picker): make the cross-profile allowlist test leak-proof The new allowlist test drove availableModels through setSessionSettingsCache, but sibling suites (ModelPicker, ProviderManager, ...) mock.module both settings.js (getSettings_DEPRECATED) and modelAllowlist.js (isModelAllowed) process-wide, so in the full sequential run the leaked stubs defeated the cache and the denied option was not filtered (smoke-and-tests red on the full suite, green in isolation). Drive the allowlist deterministically from this suite instead: install-once, gated, passthrough mocks of getSettings_DEPRECATED (the filter gate) and isModelAllowed (the per-option check), both keyed off a single activeSettingsOverride and cleared in afterEach. Same gated-passthrough pattern as the suite's existing providerConfig/providers/auth/profiles mocks and the agent.test.ts allowlist approach. * fix(model): keep cross-profile switch options out of the SDK models list getModelOptions() now returns inactive-profile entries encoded as __switch_profile__:<id>:<model>. print.ts mapped those straight into the ModelInfo list returned to SDK/web callers, exposing UI-only values that are not selectable model ids. Filter them with parseSwitchProfileValue before building modelInfos. Add ModelPicker coverage for the allowProfileSwitch filter (hidden inline, shown when allowed) and document cross-profile /model switching in the provider-profile docs. * test(model-picker): prove cross-profile switch options never reach SDK models Extract selectSdkModelOptions as the single gate the SDK modelInfos builder runs every getModelOptions() entry through, and cover it directly: an encoded __switch_profile__:<id>:<model> option is dropped while real model ids pass through. Fails if an inactive-profile affordance ever leaks into the initialize.models response again (#1119). * docs(model-picker): clarify the env gate for inactive-profile entries The inactive-profile models only appear when the provider-profile env workflow is active (CLAUDE_CODE_PROVIDER_PROFILE_ENV_APPLIED=1), not for every multi-profile setup. Spell that out and restore the local-only `--provider ollama` guidance that was folded into the paragraph. * fix(model-picker): gate SDK option filter on switchToProfileId marker selectSdkModelOptions filtered on the encoded __switch_profile__ value prefix, which also reserved that prefix for every custom model id. A real configured model whose id starts with __switch_profile__: would vanish from the SDK models response and non-switching pickers. Key the gate on the explicit switchToProfileId marker, which only synthesized switch options carry, and add the collision regression. Refs #1119 * fix(model-picker): reuse switch confirmation for cross-profile selections The cross-profile branch built its own "Switched to" message and returned before the regular path appended the selected effort and the "Billed as extra usage" notice, hiding cost-impacting feedback when a reasoning/extra-usage target was chosen through an inactive profile. Append effort and the extra-usage check to the switch confirmation. Refs #1119 * fix(model-picker): surface inactive profiles on the active Ollama path The isOllamaProvider() early return ran before the inactive-profile options were computed, so an active local Ollama profile saw only its own models and lost the cross-profile switcher, forcing the /provider round-trip this feature removes. Hoist the inactive-profile compute above the Ollama branch and append it to the Ollama returns. Refs #1119 * fix(model): surface inactive profiles on all provider branches; decode only real switch options Two follow-ups to the #1119 unified /model switcher: - inactiveProfileOptions was computed before the early-return branches but only appended on Ollama / local-scope / PAYG paths. The GitHub Copilot, NVIDIA NIM, MiniMax, Xiaomi MiMo, ant, and Claude-subscriber branches returned first, so a user with a saved profile active on any of those routes lost the cross-profile entries and had to round-trip through /provider. Append the (env-gated, so empty unless a profile is applied) inactive options on those branches too. - filterModelOptionsByAllowlist decoded any value starting with `__switch_profile__:` via parseSwitchProfileValue, even a normal custom model id that merely shares that prefix, evaluating the allowlist against the wrong inner model. Gate the decode on the `switchToProfileId` marker (the type's documented contract) so non-switch ids are checked verbatim. Extends the cross-profile harness with gated getAPIProvider / NVIDIA / subscriber overrides and adds branch-append + verbatim-allowlist regressions (red-green). * fix(model): key profile-switch handling on the marker across picker and command The allowlist/SDK paths already used the switchToProfileId marker, but two surfaces still keyed on the raw `__switch_profile__:` value prefix: - ModelPicker's inline-picker filter hid any option whose value started with the prefix, so a real custom model id like `__switch_profile__:vendor:gpt-5.4` disappeared from prompt/settings pickers. It now filters on `switchToProfileId === undefined`. - the /model command decoded parseSwitchProfileValue(model) for any prefixed string and tried to activate the encoded profile id, so selecting such a custom model activated a nonexistent profile instead of setting the literal model. It now only treats the value as a switch when the decoded profile id maps to a real configured provider profile — which every synthesized switch option does, and a prefix-colliding custom id does not. Drops the now-unused SWITCH_PROFILE_VALUE_PREFIX import from ModelPicker. Adds a picker regression (marked switch hidden, prefixed custom model stays visible) and completes the cross-profile branch coverage (MiniMax, Xiaomi MiMo, ant) so every branch that appends inactive-profile options is locked. * test(model): register target profiles in cross-profile switch tests The /model command now only treats a `__switch_profile__:` value as a switch when its decoded profile id maps to a real configured provider profile. The cross-profile switch tests set up setActiveProviderProfile but left the shared getProviderProfiles mock empty, so the new guard classified their switch values as literal models and the fast-mode / effort / extra-usage assertions no longer ran. Register each test's target profile via getProviderProfiles so the switch path executes as intended. * fix(model): gate cross-profile switches on the selected option marker Selecting a value that merely parses as `__switch_profile__:<profileId>:<model>` activated the provider whenever <profileId> existed, so a literal custom model id such as `__switch_profile__:profile_openai:gpt-5-mini` wrongly switched the active provider instead of being applied verbatim. Thread the picked option's `switchToProfileId` marker from ModelPicker.onSelect (selectOptions already carries it) and only activate a profile when the marker matches the decoded id. The effort/display resolver had the same gap — it decoded every prefixed value; gate it on a genuine marker-backed switch option too. Add a regression asserting a marker-less prefixed id is applied literally. * test(model): cover Max/Team Premium and empty-catalog switch-append paths The cross-profile branch-coverage suite exercised the populated-catalog returns but not the Max/Team Premium subscriber early return nor the empty-catalog fallbacks (NVIDIA/MiniMax/Xiaomi), which are the same paths that previously dropped the inactive-profile switch options. Lock them so every changed return that appends `...inactiveProfileOptions` is covered. * fix(model): keep inactive-profile switch options in /model discovery overrides The interactive /model command passes an optionsOverride into ModelPicker for descriptor-backed and legacy OpenAI-compatible discovery contexts, built from mergeActiveProfileModelOptions which only merges the ACTIVE profile's route models. Because the picker renders optionsOverride ?? getModelOptions(), the inactive-profile switch entries getModelOptions() appends never reached those paths, so the unified switcher vanished for provider-profile routes (OpenRouter/Kimi/MiniMax, refreshed local profiles). Re-append the same inactive-profile switch options (allowlist-filtered on the decoded target) to any override list before handing it to the picker. * fix(model): base the switch marker on the presented option, treat ties as ambiguous The picker derived switchToProfileId with selectOptions.find(value===...), and the effort/display resolver decoded when any getModelOptions() entry with the same value carried the marker. If a literal custom model id collided with an encoded switch value, the literal could borrow a different same-value option's marker and wrongly activate a provider. Add resolveSelectedSwitchProfileId, which keys on the actual presented option and treats duplicate-value matches as ambiguous (no switch), and route both the onSelect marker and the decode decision through it. |
||
|
2edec9a140 |
fix(deps): ship a zero-warning, minimal install (#1784)
* fix(deps): ship a zero-warning, minimal install
The published package declared 62 runtime `dependencies`, but `dist/cli.mjs`
is a fully-bundled esbuild output that inlines almost all of them. End users
therefore installed ~476 transitive packages — including three subtrees the
bundle never needs at install time, each emitting an install warning:
- node-domexception (deprecated) via google-auth-library
- protobufjs (allow-scripts) via @grpc/* (already bundled into dist)
- sharp (allow-scripts) native image module
The repo's `overrides`/`allowScripts` silence these locally, but those are
root-only npm settings and are ignored when the package is installed as a
dependency — so end users saw the warnings.
Core changes:
- package.json: runtime dependencies trimmed 62 -> 3 (@orama/orama,
@orama/plugin-data-persistence, @vscode/ripgrep). Bundled packages, plus
the optional sharp/google-auth-library, move to devDependencies so they
are built/tested but not shipped.
- package.json: @anthropic-ai/sdk, @modelcontextprotocol/sdk, react and
react-reconciler declared as OPTIONAL peerDependencies — externalized by
the ./sdk bundle but bundled into the CLI. Optional peers keep the CLI
install minimal and warning-free while still resolving for ./sdk consumers.
- externals.ts: sharp, google-auth-library and @anthropic-ai/bedrock-sdk
marked OPTIONAL_RUNTIME_EXTERNALS (loaded on demand, not shipped).
- validate-externals.ts: runtime deps validate against externals; bundled
deps validate against dependencies + devDependencies.
- client.ts: load @anthropic-ai/bedrock-sdk via the runtime importer so
esbuild no longer inlines it and hoists its static @aws-sdk import into
the CLI bundle (that was a startup crash for default installs).
Optional-dependency UX (consistent, actionable errors):
- New src/utils/optionalRuntimeModule.ts exports importRuntimeModule and
importOptionalRuntimeModule. The optional variant translates a missing
package (code === 'ERR_MODULE_NOT_FOUND', specifier present in message)
into "<feature> requires "<pkg>" ... Run `npm i -g <pkg>`". Generic so
typed call sites keep their module types.
- Routed ALL optional-package load sites through it (previously only one
did): google-auth-library (client.ts, auth.ts, geminiAuth.ts),
@anthropic-ai/foundry-sdk + @azure/identity (client.ts), and the
@aws-sdk/* Bedrock paths (model/bedrock.ts, tokenEstimation.ts, aws.ts).
- imageProcessor.ts: sharp-missing error now says `npm i -g sharp`.
- docs/advanced-setup.md: new "Optional provider packages" table and a
Vertex note documenting the on-demand installs.
- Unit test for the helper (friendly error, success path, specifier match,
raw passthrough).
- knip.json: ignore google-auth-library (now loaded via runtime string).
Verified on the current tree:
- tsc, build/validate-externals, knip, and tests all pass.
- npm pack + install --omit=dev adds 8 packages, zero deprecation/
allow-scripts/funding warnings; --version/--help/mcp list run.
- With packages absent, CLAUDE_CODE_USE_BEDROCK and CLAUDE_CODE_USE_VERTEX
print the friendly `npm i -g <pkg>` error (verified end-to-end).
- ./sdk imports once its optional peers are present (24 exports, no warns).
- Bundled ajv + ajv-formats validate with no ajv installed; no unguarded
native runtime requires (fsevents absent in chokidar 4; bun:sqlite Bun-only).
Trade-off: image reads, AWS Bedrock, Azure Foundry and GCP/Vertex now prompt
a one-time `npm i -g <pkg>` instead of being shipped to every user.
Co-Authored-By: OpenClaude <openclaude@gitlawb.com>
Review fixes (CodeRabbit + jatmn):
- validate-externals: the INTENTIONALLY_BUNDLED exemption is now scoped per
bundle. The CLI exempts every bundled package; the SDK does NOT exempt
packages declared as peerDependencies (keyed on package.json, an independent
source of truth) so dropping react/@anthropic-ai/sdk from SDK_EXTERNALS now
fails validation instead of silently passing. Added an explicit minimal-
install contract check: bundled packages must be devDependencies-only — never
in `dependencies`, and only the SDK-external subset may be optional peers.
Validation logic extracted to scripts/externalsValidation.ts + tests.
- FileReadTool oversized-image fallback now loads via the shared
getImageProcessor() (not a raw import('sharp')) and re-throws
ImageProcessorUnavailableError, so a missing processor surfaces the
`npm i -g sharp` install hint instead of returning an over-budget image.
- optionalRuntimeModule: match the missing specifier as a QUOTED token, not a
raw substring, so a missing transitive package whose name contains the
requested one (sharp vs sharp-libvips, @aws-sdk/client-bedrock vs
@aws-sdk/client-bedrock-runtime) no longer triggers the wrong install hint.
Predicate extracted to isMissingSpecifierError() with regression tests.
- docs/advanced-setup.md: the Vertex auth section now shows both documented
paths (gcloud ADC and a GOOGLE_APPLICATION_CREDENTIALS service-account file).
Review fixes (round 2, CodeRabbit):
- validate-externals: assert the optional-peer install contract — every
peerDependency must be { optional: true } in peerDependenciesMeta
(validateOptionalPeers), so losing that flag fails the build instead of
silently reintroducing install warnings.
- validate-externals: hard-check OPTIONAL_RUNTIME_EXTERNALS placement
(validateOptionalRuntimeexternals). Anything esbuild can see statically must
stay external in BOTH bundles (dropping sharp/google-auth-library now fails);
the runtime-indirection-only subset (new RUNTIME_INDIRECTION_ONLY_EXTERNALS)
must stay OUT of externals so esbuild never re-exposes their static imports.
- Deeper-dig fix: @anthropic-ai/foundry-sdk was misclassified as
INTENTIONALLY_BUNDLED, but it is loaded only through the Function indirection
(esbuild never sees it, so it was never actually bundled) — its sole presence
in dist is the specifier string. Per the PR's own "Azure Foundry now prompts"
trade-off it is on-demand, so it now lives in OPTIONAL_RUNTIME_EXTERNALS +
RUNTIME_INDIRECTION_ONLY_EXTERNALS (mirroring bedrock-sdk). sandbox-runtime is
genuinely statically imported, so it stays bundled.
- Provider-routing coverage (scripts/optionalRuntimeSpecifiers.test.ts): a
static scan asserts every importOptionalRuntimeModule specifier is a declared
OPTIONAL_RUNTIME_EXTERNAL and never also INTENTIONALLY_BUNDLED — the
invariant that keeps a provider's optional package loadable on demand.
- All new validators extracted to scripts/externalsValidation.ts with tests.
Review fixes (round 3, CodeRabbit):
- client.ts: gate the Vertex google-auth-library import behind the non-skip
branch. CLAUDE_CODE_SKIP_VERTEX_AUTH (proxy/test) uses a mock GoogleAuth and
must not require the optional package; it was loaded unconditionally before.
- optionalRuntimeModule: drop the hard-coded `npm i -g`. The helper backs both
the global CLI and project-local ./sdk consumers, so the hint is now
context-neutral ("npm install <pkg>" / add -g for the global CLI).
- validate-externals: every SDK_ONLY_EXTERNALS entry must STAY a
peerDependency (a dropped peer leaves runtimeDeps while the SDK still
externalizes it); and OPTIONAL_RUNTIME_EXTERNALS must never be shipped (fail
on overlap with dependencies/peerDependencies). Both with tests + live-verified.
- optionalRuntimeSpecifiers.test: pin the EXACT set of optionally-loaded
specifiers instead of a >=5 count (a count passes even if a provider path
regresses).
- attachments: extract tryReadEditedImageAttachment() — background watched-file
image attachments DEGRADE to null on any failure (incl.
ImageProcessorUnavailableError) so a missing optional package never aborts a
turn, while the explicit FileReadTool path still surfaces the install hint.
Deterministic regression test (bad path -> null).
- docs: Bedrock row notes profile-based auth also needs
@aws-sdk/credential-providers; install-hint wording matches the new message.
Review fixes (round 4, CodeRabbit):
- attachments: stop sending the raw file path through the analytics
bypass-cast (tengu_watched_file_compression_failed). Send only the safe
file extension via getFileExtensionForAnalytics, matching the existing
tengu_file_read_dedup pattern, so no usernames/project paths can leak.
- externals.ts: corrected the OPTIONAL_RUNTIME_EXTERNALS header comment,
which still claimed all entries "remain in COMMON_EXTERNALS" — no longer
true since the indirection-only subset (bedrock/foundry) must stay OUT of
the externals lists.
(Other CodeRabbit comments on this push re-surface items already addressed in
prior commits: the peerDependenciesMeta-optional check (validateOptionalPeers),
the SDK-peers-present and optional-not-shipped validator rules, the
exact-specifier-set test, the attachments degrade contract + test, and the
context-neutral install hint are all present. The "assert every optional
external is a devDependency" suggestion is intentionally NOT applied: @aws-sdk/*
and @azure/identity are transitive devDeps via bedrock-sdk/foundry-sdk, so a
blanket assertion would be incorrect; source resolution is covered by the
build + tests that import these packages.)
Review fixes (round 5, CodeRabbit):
- attachments: stop leaking file paths via logError in the background-image
degrade path. readImageWithTokenBudget can throw path-bearing messages
(e.g. "Image file is empty: <path>") and logError persists message/stack, so
log only the error TYPE name now. (Analytics payload was already sanitized.)
- attachments: tryReadEditedImageAttachment takes an injectable reader so the
degrade contract is tested for the EXACT error types — ImageProcessorUnavailableError
and a path-bearing read error both degrade to null (not just ENOENT) — plus a
success case. No mocking.
- validate-externals: enforce the source-install half of the optional contract.
Non-transitive OPTIONAL_RUNTIME_EXTERNALS must be devDependencies so `bun
install` source builds resolve them. The new TRANSITIVE_OPTIONAL_EXTERNALS
documents the exemption (@aws-sdk/* via @anthropic-ai/bedrock-sdk, @azure/identity
via @anthropic-ai/foundry-sdk — provided transitively, not direct devDeps). A
blanket "all optionals are devDeps" check would have wrongly failed on those.
Tests + live-verified (dropping sharp from devDependencies now fails).
Review fixes (round 6, CodeRabbit + jatmn):
- optionalRuntimeSpecifiers.test: the call-site scan regex missed
generic-annotated calls (importOptionalRuntimeModule<...>(...)) in
model/bedrock.ts and tokenEstimation.ts, so the exact-set assertion was
incomplete. Regex now allows an optional generic; EXPECTED_SPECIFIERS adds
@aws-sdk/client-bedrock and @aws-sdk/client-bedrock-runtime (7 total).
- importOptionalRuntimeModule default generic is now <T = unknown> (was any),
so destructured imports are no longer silently any. Every call site now
supplies its module type — typeof import('<pkg>') where the package is
type-resolvable (bedrock-sdk, foundry-sdk, @aws-sdk/credential-providers,
google-auth-library), and a named minimal-shape alias for @azure/identity
(not a direct devDep, so typeof import can't resolve it). This gives
compile-time verification of each provider's module contract (export names,
shapes) — the structural answer to the "cover the provider branches" ask.
- attachments: tryReadEditedImageAttachment takes injectable {read,log,track};
a new test asserts the sanitized-telemetry contract directly — the logError
payload is path-free and the analytics payload carries only `ext`, never the
edited-image path.
* fix(deps): address optional runtime review findings
* test(deps): isolate optional runtime importer mocks
* fix(deps): clarify AWS optional auth labels
* fix(deps): close optional runtime review gaps
---------
Co-authored-by: jatmn <the@jat.mn>
|
||
|
JATMNandGitHub
|
cd13a61537 |
fix(memory): recover from autocompact overflow failures (#1858)
* fix(memory): recover from autocompact overflow failures * fix(memory): address autocompact review findings * fix(memory): close autocompact recovery gaps * fix(memory): reduce OpenAI conversion pressure * test(memory): add long-session guard smoke * fix(memory): add runtime memory guard diagnostics * fix(memory): surface autocompact failure diagnostics * fix(memory): reuse hard-cap resolver in diagnostics * fix(memory): avoid hard-cap diagnostic drift * fix(memory): clarify hard-cap diagnostics |
||
|
BogdanandGitHub
|
5226fb9ee7 |
fix(query): configure hard max and abort reasons (#1850)
* fix(query): configure hard max and abort reasons * fix(query): normalize legacy abort reasons * test(query): dedupe abort classification setup |
||
|
BogdanandGitHub
|
8182a46441 | feat(report): render task reports as markdown (#1826) | ||
|
259c7ec27a |
fix(ollama): preserve chat history with native context (#1805)
* fix(ollama): preserve chat history with native context Route Ollama chat requests through the native /api/chat endpoint so OpenClaude can send request-level options.num_ctx instead of relying on Ollama's OpenAI-compatible shim. Default the Ollama request context to 32768 tokens, support OPENCLAUDE_OLLAMA_NUM_CTX and OLLAMA_CONTEXT_LENGTH overrides, and map max tokens/temperature/top_p into native Ollama options. Adapt native Ollama streaming and non-streaming responses back into the existing OpenAI-shaped conversion pipeline, including usage, text, structured tool calls, and tool_use stop reasons. Normalize native Ollama request messages for images and historical tool calls, avoiding OpenAI-only image_url/id/type payload fields in /api/chat requests. Add Ollama context diagnostics, loopback-only ollama ps status checks, regression coverage, and documentation for verifying active context length. * fix(ollama): address native routing review feedback * fix(ollama): restrict loopback host matching * fix(ollama): exclude wildcard bind address * fix(ollama): keep https localhost proxies on chat completions --------- Co-authored-by: jatmn <12479882+jatmn@users.noreply.github.com> |
||
|
BogdanandGitHub
|
a47493342f |
feat(report): generate deterministic session task reports (#1802)
* feat(report): generate deterministic session task reports * fix(report): address task report review findings * fix(report): stabilize task report paths on Windows * test(report): expect redacted git metadata cwd * test(report): assert literal redacted git cwd * fix(report): capture PowerShell and backgrounded validations * fix(report): detect quoted validation commands * fix(report): reconcile background validation notifications * fix(report): keep foreground command statuses authoritative * test(report): assert command status precedence |
||
|
JATMNandGitHub
|
dd4c4abc81 |
feat(api): add OpenAI-compatible credential pool failover (#1706)
* feat(api): rotate OpenAI credential pools * fix(api): align pooled credential discovery * fix(cache-probe): preserve GitHub credential precedence * fix(provider): honor pooled OpenAI fallbacks * fix(provider): validate pooled profile credential labels * fix(api): harden OpenAI credential pool handling Reject placeholder values in pooled OpenAI credentials before requests, discovery, diagnostics, and profile generation can use them. Normalize pooled credentials to a single usable key for model discovery, runtime cache partitions, cache probing, and NVIDIA NIM cache lookups. Preserve documented profile precedence by letting live shell credentials override saved pools, carrying OpenCode fallback pools through launch, and redacting individual pool members in profile display. Add regression coverage for pooled credential validation, profile launch/rebuild behavior, discovery/cache callers, diagnostics, provider autodetect, and shim failover semantics. * fix(provider): cover pooled key recommendation path Import the pooled OpenAI credential validator in provider-recommend and split invalid credentials from unset credentials in user guidance. Add a script-level regression that runs the OpenAI recommendation path with OPENAI_API_KEYS so the ts-nocheck script cannot regress with runtime ReferenceErrors. Scrub pooled OpenAI keys before xAI OAuth profile env construction and loosen the invalid-pool discovery test to assert auth header absence instead of exact header shape. * fix(tests): stabilize rebased provider checks * fix(provider): address pooled credential review findings * test(api): cover opencode go credential failover * fix(provider): share OpenAI credential usability checks * fix(provider): respect pooled credential precedence * fix(model): preserve pooled discovery credential precedence * fix(model): fall back from unusable pooled discovery keys |
||
 euxaristiaandGitHub
|
38b0e27333 |
fix(opencode-go): sync model catalog with opencode.ai/go (#1745)
* fix(opencode-go): sync model catalog with opencode.ai/go The OpenCode Go subscription page (https://opencode.ai/go) lists 13 models, but the catalog had 20. Remove the 7 models no longer offered: glm-5, kimi-k2.5, minimax-m2.5, qwen3.5-plus, mimo-v2-pro, mimo-v2-omni, hy3-preview. Catalog now matches the page exactly: - OpenAI-compatible: GLM 5.2, GLM 5.1, Kimi K2.7 Code, Kimi K2.6, DeepSeek V4 Pro, DeepSeek V4 Flash, MiMo V2.5 Pro, MiMo V2.5 - Anthropic messages: MiniMax M3, MiniMax M2.7, Qwen3.7 Max, Qwen3.7 Plus, Qwen3.6 Plus Updates gateway catalog, model descriptors, generated artifacts, and tests. * fix(opencode-go): reorder model catalog to match opencode.ai/go listing Reorder both the gateway catalog and model descriptor lists to match the order models appear on https://opencode.ai/go, so the in-app model picker mirrors the subscription page. No model added or removed — purely a reorder. GLM-5.2 → Qwen3.7 Max → Kimi K2.7 Code → MiMo V2.5 Pro → DeepSeek V4 Pro → Qwen3.7 Plus → MiniMax M3 → MiMo V2.5 → DeepSeek V4 Flash → GLM 5.1 → Kimi K2.6 → Qwen3.6 Plus → MiniMax M2.7 * test(opencode-go): assert exact model set matches opencode.ai/go catalog Address CodeRabbit review on #1745 — the count-only test wouldn't catch catalog drift. Add a strict set assertion verifying the 13 expected IDs are present and no removed/unexpected IDs remain. * test(opencode-go): update Anthropic Messages route test for refreshed catalog The direct-env-routing test listed minimax-m2.5 and qwen3.5-plus, which were removed from the opencode-go catalog. Replace with the five /messages-endpoint models that remain: minimax-m3, minimax-m2.7, qwen3.7-max, qwen3.7-plus, qwen3.6-plus. Unblocks the smoke-and-tests CI check on #1745. * fix: update OpenCode Go model references to 13 models and add assertions |
||
|
JATMNandGitHub
|
5625f4217d |
fix: preserve provider route context metadata (#1741)
* fix: preserve provider route context metadata Resolve issue #1732 by keeping active provider-profile routes attached during context limit resolution and making gateway-prefixed model IDs resolve against provider-scoped metadata instead of falling through to global aliases. Preserve composite provider-path suffixes such as accounts/fireworks/models/... and fireworks/models/... before generic last-segment matching, so wrapped gateway IDs resolve Fireworks-specific limits instead of generic descriptors. Refresh OpenCode Zen and OpenCode Go catalog metadata, including route-specific context/output limits, regenerate integration artifacts, add DeepSeek V4 Pro on NVIDIA NIM, add the Gemini 3.1 Pro router alias, and update user-facing OpenCode model counts. Scope OpenCode descriptor default model names to OpenCode routes via providerModelMap so unprefixed vendor lookups are not hijacked by gateway descriptors. Add wrapper-path assertions for the user-facing max output token helper. Add regression coverage for provider-prefixed gateway models, active-profile route preservation, account-qualified composite paths, and OpenRouter-wrapped fireworks/models/... paths. Harden Windows/full-suite validation by normalizing plugin hook display paths and resetting status-redaction HOME/USERPROFILE state. Validation: bun install; bun run build; bun run smoke; bun run typecheck; bun run typecheck:type-tests; bun run check (4634 pass, 0 fail); bun run test:provider (857 pass, 0 fail); bun run test:provider-recommendation (91 pass, 0 fail); bun run integrations:check; bun run security:pr-scan -- --base upstream/main; git diff --check. Follow-up validation: bun test src/integrations/runtimeMetadata.test.ts --max-concurrency=1; bun test src/utils/context.test.ts src/integrations/runtimeMetadata.test.ts src/integrations/gateways/opencode.test.ts --max-concurrency=1; bun run test:provider; bun run integrations:check; bun run typecheck; git diff --check. # Conflicts: # src/integrations/gateways/opencode-go.ts # src/integrations/models/opencode.ts * fix: align OpenCode context metadata Refresh OpenCode Zen and Go descriptor context/output limits against the live OpenCode model lists and Models.dev provider metadata. Add a regression assertion for provider-specific OpenCode limits so route-scoped metadata does not fall back to generic model budgets. * fix: remove duplicate Gemini model descriptor Keep the canonical Gemini 3.1 Pro descriptor and rely on provider-prefixed suffix matching for google/gemini-3.1-pro runtime lookups. Also separate the OpenCode limit regression test from the following assertion for readability. * fix: preserve OpenCode Go messages auth metadata * test: cover OpenCode Go review cases |
||
|
BogdanandGitHub
|
7c034c5a62 |
feat: add redacted diagnostic issue reports (#1647)
* feat: add redacted diagnostic issue reports * fix: address diagnostic report review feedback * fix: report Codex runtime diagnostics accurately |
||
|
BogdanandGitHub
|
d8dbf274b4 |
chore(runtime): align Node.js minimum version (#1644)
* chore(runtime): align Node.js runtime requirements * test(runtime): cover prefixed Node versions * fix(runtime): check node executable in doctor |
||
|
JATMNandGitHub
|
de726c43e1 |
Fix custom provider context discovery (#1620)
* Fix custom provider context discovery Teach the custom OpenAI-compatible gateway to discover context windows from /v1/models metadata, including LiteLLM model_info context_length and max_input_tokens fields. Use cached discovery metadata when resolving runtime context and output limits, with sync cache reads kept memoized and partitioned by endpoint, credential, and custom headers. Add provider-profile maxContextLength env overrides and document LiteLLM context metadata plus the CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS fallback. Cover startup discovery, runtime cache lookup, custom gateway parsing, profile overrides, and env custom-header cache partitioning with focused tests. * Fix discovery smoke test isolation Clear CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC during discovery service test setup so full-suite environment state cannot force startup discovery down the nonessential-traffic skip path. Verified with: - bun test ./src/integrations/discoveryService.test.ts - CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 targeted startup discovery test - bun run smoke - bun run typecheck * Partition custom discovery startup test cache Use a test-only custom header in the startup custom route discovery test so it exercises network discovery even when the full suite has pre-seeded the no-header custom discovery cache key. Verified with: - bun test ./src/integrations/discoveryService.test.ts - CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 targeted startup discovery test - bun run smoke - bun run typecheck * Fix profile context override lifecycle Add CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS to managed profile cleanup so switching profiles clears stale context-window overrides, including same-model OpenAI-compatible switches. Preserve persisted context-window overrides when rebuilding OpenAI-compatible startup env after restart. Verified with: - bun test src/utils/providerProfile.test.ts src/utils/providerProfiles.test.ts - bun run typecheck - bun run smoke * Detect profile context override drift Include CLAUDE_CODE_OPENAI_CONTEXT_WINDOWS in OpenAI-compatible active-profile env alignment so managed profiles with maxContextLength are re-applied when the override is missing or stale. Verified with: - bun test src/utils/providerProfiles.test.ts - bun run typecheck - bun run smoke |
||
 
|
0b24b60ce9 |
feat(provider): add Fireworks AI as official OpenAI-compatible provider (#1590)
* feat(provider): add Fireworks AI as official OpenAI-compatible provider
Includes vendor descriptor, brand descriptor (276 models), model
descriptors (full + merged), routing metadata, env auto-detection,
profile support, client defaults, and docs.
* test: add focused regression tests for Fireworks AI auth and routing
- Add 7 env-only routing tests in client.test.ts (shim routing,
stale model replacement, base URL override, shim option cleanup,
non-Fireworks override ignored, priority with MiniMax, Bedrock yield)
- Add FIREWORKS_API_KEY auto-detection test in providerAutoDetect.test.ts
- Add profile apply/persistence/env-drift tests in providerProfiles.test.ts
- Fix FIREWORKS_API_KEY propagation in strictEnv early return path
* fix: address reviewer comments on Fireworks integration
- Remove OPENAI_API_KEY exclusion so Fireworks cred wins over stale OpenAI key
- Fix TS type error in test by using String() wrapper
- Add Fireworks to detection priority comment in providerAutoDetect.ts
- Add useFireworksEnvOnlyProvider to shim condition for pattern consistency
- Replace loose .includes('fireworks.ai') with isFireworksBaseUrl() exact hostname check
* fix: add explicit case 'fireworks' in applyProviderFlag for credential precedence
- Add 'fireworks' to PREFERRED_PROVIDER_ORDER
- Add case 'fireworks' with dedicated key winning pattern (mirrors atlas-cloud)
- Add FIREWORKS_API_KEY to copiedOpenAIKeyProvider detection so stale
keys are cleaned up when switching away from Fireworks
* fix: guard fireworks defaultModel assignment against 'undefined' string coercion
* fix: remove leftover conflict marker in providerProfiles.ts
* docs(fireworks): add JSDoc to Fireworks functions for coderabbit docstring coverage
Adds JSDoc annotations to isFireworksBaseUrl, getFireworksBaseUrlOverride,
hasFireworksEnvOnlyProviderIntent, isFireworksModelName, and
applyFireworksEnvOnlyDefaults.
* fix(fireworks): cross-check NEARAI_API_KEY in env-only intent functions
hasNearaiEnvOnlyProviderIntent and hasFireworksEnvOnlyProviderIntent were
missing mutual cross-checks. When both NEARAI_API_KEY and FIREWORKS_API_KEY
are set, neither excludes the other, and nearai silently wins by ordering.
Adding !hasNonEmptyEnvValue(processEnv.FIREWORKS_API_KEY) to the nearai intent
and !hasNonEmptyEnvValue(processEnv.NEARAI_API_KEY) to the fireworks intent
ensures both return false, forcing explicit provider selection.
* fix(fireworks): fix typo in JSDoc — OPENAI_API_API_BASE -> OPENAI_API_BASE
* fix(fireworks): remove merge artifact and preserve no-key auth headers
- src/utils/providerAutoDetect.ts: remove leftover ======= conflict
marker and stale duplicate priority lines
- src/utils/providerProfiles.ts: preserve apiFormat, authHeader,
authScheme, authHeaderValue in the no-key OpenAI-compatible
fallback path so saved Responses mode / custom auth config
survives restart
* fix: Fireworks env-only startup preservation and MIMO priority comment
- Add FIREWORKS_API_KEY check to hasConcreteProviderSelection() so env-only
Fireworks setup is not overwritten by Gitlawb Opengateway default
- Add regression test verifying FIREWORKS_API_KEY survives no-profile startup
- Fix providerAutoDetect.ts priority comment to include MIMO_API_KEY (position 8)
and renumber subsequent entries to match actual detection order
* fix: also preserve env-only NEAR AI startup in hasConcreteProviderSelection()
* fix: remove duplicate Fireworks model descriptor, add FIREWORKS_API_KEY to test env cleanup
* fix: move duplicate model check to generation-time, add OPENAI_AUTH_* env cleanup to test harness
---------
Co-authored-by: Gravirei <gravirei@users.noreply.github.com>
|
||
|
|
eacc7d8fac |
feat: add NEAR AI provider integration (#1594)
* feat: add NEAR AI provider integration
- Create vendor, brand, and model descriptors for NEAR AI (22 models)
- Add NEAR AI to route metadata, client, provider auto-detect, and profiles
- Update compatibility tests and ProviderManager test PRESET_ORDER
- Add README and docs entries for NEAR AI provider
- Update .env.example with NEAR AI configuration
* fix: address CodeRabbit review comments
- Fix .env.example: change 'Option N' to 'Option 11' in quick reference
- Narrow isNearaiModelName to use explicit NearAI model prefixes instead of broad includes('/')
- Add NEARAI_API_KEY propagation in strictEnv startup path
* fix: align NEAR AI validation host matching with wildcard subdomain routing
- Add *.completions.near.ai to matchBaseUrlHosts in vendor descriptor
- Add matchHostnameAgainstRouteHosts helper with wildcard (*.) prefix support
- Use helper in both resolveRouteIdFromBaseUrl and getRuntimeValidationTarget
- Add regression test for qwen35-122b.completions.near.ai TEE endpoint
- Add NEARAI_API_KEY to test env cleanup list
* fix: align Near AI integration with env-only provider best practices
- Replace loose .includes('near.ai') with isNearaiBaseUrl() in providerProfiles.ts
for exact hostname validation (all 4 instances)
- Add NEARAI_API_KEY to copiedOpenAIKeyProvider detection in providerFlag.ts
- Add case 'nearai' to applyProviderFlag switch with dedicated key precedence
- Add 'nearai' to PREFERRED_PROVIDER_ORDER
- Add useNearaiEnvOnlyProvider to OpenAI shim condition in client.ts
- Remove OPENAI_API_KEY exclusion from hasNearaiEnvOnlyProviderIntent (dedicated
key wins over stale generic key, consistent with xAI pattern)
- Update detection priority comment in providerAutoDetect.ts to include
MIMO_API_KEY, XAI_API_KEY, and NEARAI_API_KEY
* fix: add exact completions.near.ai host to isNearaiBaseUrl
* fix: add higher-precedence provider key exclusions to hasNearaiEnvOnlyProviderIntent
* fix: add OPENAI_API_KEY and MINIMAX_API_KEY exclusions to hasNearaiEnvOnlyProviderIntent
* fix(near-ai): don't let stale OPENAI_API_KEY suppress Near AI routing
---------
Co-authored-by: Gravirei <gravirei@users.noreply.github.com>
|
||
|
JATMNandGitHub
|
14036209cd |
Add configurable message-count compaction (#1587)
* Add configurable message-count compaction Add a /config setting for opting into message-count-based compaction thresholds and persist it in global config. Disable the legacy OPENCLAUDE_MAX_ACTIVE_MESSAGES default unless the new setting is off and the environment variable is explicitly set. Add a timeout around forked compact summaries using a child abort controller so timeouts and user aborts clean up without affecting the main thread. Document the diagnostic setting and normalize trailing line endings in Windows alias docs/script. * Address compaction PR review feedback Add a shared literal enum and normalizer for message-count compaction thresholds, use it in config, /config UI, and query threshold handling. Move the compact timeout constant to module scope and mark the /config docs snippet with a text fence. |
||
|
286d403093 |
Update(zen-go): add claude-opus-4-8, minimax-m3, mimo-v2.5-free models and proper effort level integration for Zen/Go models (#1505)
* feat(provider): add OpenCode Zen/Go subscription support
Add OpenCode as a first-class provider, enabling users to connect their
Zen (pay-as-you-go) and Go ($10/mo) subscriptions via the /provider command.
New integration descriptors:
- vendors/opencode.ts — OpenCode Zen vendor (41 models)
- gateways/opencode-go.ts — OpenCode Go gateway (12 models)
- brands/opencode.ts — brand descriptor
- models/opencode.ts — full model catalog (GPT, Claude, Gemini, Qwen,
GLM, Kimi, MiniMax, Grok, DeepSeek, MiMo, Nemotron)
Modified files:
- integrationArtifacts.generated.ts — register descriptors and presets
- providerProfile.ts — add OPENCODE_API_KEY env/secret key, 'opencode'
profile type, and buildLaunchEnv handler
- providerConfig.ts — add DEFAULT_OPENCODE_BASE_URL constants
Auth: OPENCODE_API_KEY env var or interactive key entry in /provider
Transport: openai-compatible (chat_completions)
Base URLs: https://opencode.ai/zen/v1 (Zen), /zen/go/v1 (Go)
* feat(provider): add [Zen]/[Go] tags to OpenCode preset labels
Add visual tags in the /provider preset selection to distinguish
OpenCode Zen (pay-as-you-go) from OpenCode Go (subscription).
* feat(provider): enable dynamic model discovery for OpenCode
Switch OpenCode vendor and Go gateway from static to hybrid model
catalog with openai-compatible discovery. Models are fetched from
/v1/models on startup and cached for 1 hour. Manual refresh is
supported via the /provider UI.
Static model list is preserved as fallback when discovery fails.
* test(provider): add comprehensive OpenCode Zen/Go test suite
97 tests across 2 files covering:
Integration tests (72 tests):
- Vendor descriptor: id, label, classification, base URL, model, auth,
transport, preset, validation, catalog, discovery, usage metadata
- Gateway descriptor: id, label, vendorId, category, base URL, model,
auth, transport, preset, catalog, discovery
- Brand descriptor: id, label, canonicalVendorId, capabilities, modelIds
- Model catalog: registration, vendor/gateway associations, required
fields, valid classifications, reasoning/coding tags, no duplicates,
model counts (41 Zen, 12 Go), modelDescriptorId consistency
- Cross-reference: brand↔model, vendor↔model, gateway↔model,
shared OPENCODE_API_KEY
- Registry validation: no errors, no preset conflicts
- Edge cases: unique ids, unique apiNames, non-empty labels, valid
contextWindow/maxOutputTokens, valid defaultModel format, validation
message content, discovery config
Profile tests (25 tests):
- Type guard: isProviderProfile('opencode'), rejects invalid values
- buildLaunchEnv: persisted env, defaults, process env precedence,
OPENCODE_API_KEY mapping, whitespace/null/undefined/empty handling,
very long keys, special characters, concurrent access, boundary
values, no credential leakage
* fix(provider): add per-model endpoint routing (P1)
Add endpointPath field to OpenAIShimTransportConfig so catalog entries
can specify which API path to use per model. This addresses the
maintainer's [P1] finding that all models were routed to
/chat/completions regardless of their upstream endpoint.
Changes:
- descriptors.ts: add endpointPath?: string to OpenAIShimTransportConfig
- openaiShim.ts: buildRequestUrl checks shimConfig.endpointPath first
- vendors/opencode.ts: add transportOverrides to 31 catalog entries
(GPT→/responses, Claude/Qwen→/messages, Gemini→/models/<id>)
+ switch to source: 'static' to prevent free models from live API
- gateways/opencode-go.ts: add transportOverrides to 4 entries
(MiniMax/Qwen→/messages) + switch to source: 'static'
- opencode.test.ts: update tests for static source, remove discovery tests
* refactor(opencode): model OpenCode Zen/Go as gateways (P2)
* docs(provider): document OpenCode setup and move badge metadata to descriptors
- Add OpenCode Zen/Go rows to README supported providers table
- Add OpenCode Zen/Go examples and OPENCODE_API_KEY to advanced-setup.md
- Add PresetBadge type to descriptor/manifest with badge propagation in
artifact generator
- Move 4 hard-coded preset badges ([FREE], [Sponsor], [Zen], [Go]) from
ProviderManager.tsx into descriptor preset metadata
- Add badge field to providerUiMetadata so UI components read from manifest
- Update integration overview docs to recommend preset.badge for future
gateways
* fix(provider): match request body to endpoint format for OpenCode /messages and /responses (P1)
Extend the openaiShim transport so that endpointPath overrides select
both the URL and the correct body/response format:
- /responses → OpenAI Responses API body (input, max_output_tokens)
- /messages → Anthropic Messages API body (content blocks, system, max_tokens)
Also fixes: abort listener leak in SSE passthrough, system prompt
content-block flattening, and removes [Zen]/[Go] badge entries (P3).
Co-Authored-By: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com>
* fix(provider): add Google AI SDK body/response format for OpenCode Zen Gemini models (P1)
The three Gemini models in the OpenCode Zen catalog (gemini-3.5-flash,
gemini-3.1-pro, gemini-3-flash) were sending chat-completions body to
the /models/gemini-* endpoint, which expects Google AI SDK format.
- effectiveTransport now detects /models/gemini- endpointPath → 'gemini'
- buildGeminiBody() converts Anthropic messages → Google contents[]
with role mapping, systemInstruction, generationConfig, functionDeclarations
- geminiSseToAnthropic() parses Google SSE frames → Anthropic stream events
with text deltas, functionCall tool_use, finishReason mapping
- _convertGeminiToAnthropicResponse() for non-streaming responses
- Streaming/non-streaming routing via URL detection (/models/gemini-)
- serializeBody(), hasToolsPayload, omitGeminiTools all updated
* fix: prevent OpenCode model descriptors from shadowing canonical limits
P1: Prefix all defaultModel values in opencode.ts with 'opencode-'
so the fallback findModelDescriptorForApiName() doesn't match
canonical model names. The OpenCode descriptors are still found
via catalog entry lookup when the OpenCode route is active.
P2: Add 'OpenCode Go' and 'OpenCode Zen' to PRESET_ORDER in
ProviderManager.test.tsx between 'OpenAI' and 'OpenRouter'
so navigateToPreset() sends the correct number of j keypresses.
* fix: align OpenCode Go descriptor metadata with Zen
- category: 'hosted' → 'aggregating' (both are aggregating gateways)
- add validation block with OPENCODE_API_KEY guidance
- update test assertion from 'hosted' to 'aggregating'
* fix: accept OPENAI_API_KEY as fallback in OpenCode validation
When users set up OpenCode Zen/Go via /provider, the key is saved as
OPENAI_API_KEY (via buildCompatibilityProcessEnv). The validation block
only checked OPENCODE_API_KEY, causing a startup warning even though
the runtime auth header had the key it needed.
Add OPENAI_API_KEY to validation.credentialEnvVars for both gateways,
matching the pattern used by Hicap and Gitlawb Opengateway.
* chore: trigger mergeability recheck
* feat(shim): forward effort/thinking to OpenCode Zen/Go endpoints
- buildResponsesBody: add reasoning_effort + reasoning_summary + include
- buildAnthropicMessagesBody: add thinking config (adaptive/enabled/budget)
- buildGeminiBody: add thinkingConfig with thinkingLevel mapping
- modelSupportsEffort: allow OpenCode Claude and Gemini models
- modelSupportsMaxEffort: add opus-4-7
- getAvailableEffortLevels: show standard levels for OpenCode native models
- opencode-go: add missing validation block
* feat: update OpenCode Zen and Go model counts, add new models, and enhance effort level handling
* feat: implement xhigh effort support for specific models and adjust effort level handling
* fix(effort): address reviewer feedback on xhigh + new models
- docs/advanced-setup.md: bump OpenCode Go count 12 → 13
- openaiShim.ts: include opus-4-8 / opus-4.8 in the adaptive thinking
detection so the new model uses the adaptive + effort path instead
of falling back to budgetTokens
- effort.ts: modelUsesOpenAIEffort now also rejects models that include
'claude-' or 'gemini-' — without this, OpenCode Claude/Gemini
routes (provider=openai) were misclassified as OpenAI-style and
could leak xhigh past the new gate
- effort.codex.test.ts: lock in the new exclusion with a regression
test against the openai provider
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): address reviewer feedback on xhigh effort + new models
Closes the three P2 findings from PR #1505 review:
1. Settings schema now accepts 'xhigh' so a persisted xhigh survives
restart instead of being silently dropped by .catch(undefined).
2. ModelPicker /effort cycle is driven by getAvailableEffortLevels(model)
instead of a boolean includeMax, so models supporting xhigh
(opus-4-7/4-8, OpenAI/Codex) can actually select it from the picker.
displayEffort clamp now uses the available levels list, so stale
xhigh also clamps to high when the focused model doesn't support it.
3. SDK/control metadata uses getAvailableEffortLevels(model) instead of
the EFFORT_LEVELS fallback that advertised xhigh to every max-capable
model. SDK schema + generated types extended to include 'xhigh'.
Also fixes a latent generator bug: the array case in generate-sdk-types
now parenthesizes union/intersection elements so the trailing [] binds
the whole type, e.g. ("a"|"b")[] rather than "a"|"b[]. Without this,
the regenerated xhigh levels ended up typed as the single-literal
"xhigh"[] and broke the modelInfo assignability check.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(effort): order xhigh before max in EFFORT_LEVELS
EFFORT_LEVELS now matches getAvailableEffortLevels() output order
(['low', 'medium', 'high', 'xhigh', 'max']), and the order asserted by
the existing effort.codex.test.ts tests.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* chore(effort): order xhigh before max in settings + SDK schemas
Matches the EFFORT_LEVELS / getAvailableEffortLevels order from the
previous commit. The Zod enum order doesn't affect runtime validation,
but keeps the source consistent and avoids confusion if anyone reads
the enum literal to infer display order.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): clamp ModelPicker selection and mark xhigh as current
- ModelPicker.handleSelect: clamp the emitted/persisted effort to the
focused model's available levels so a toggled-but-unsupported level
(e.g. 'xhigh' on a model that doesn't support it) is never written
to settings.json or handed to the consumer. Add focusedAvailableLevels
+ focusedDefaultEffort to the memo guard so the function regenerates
when the focused model changes.
- EffortPicker: compare the xhigh option against the persisted 'xhigh'
level directly. The 'max' alias path is kept only for legacy
settings.json values that still hold 'max' from before xhigh was
introduced.
* docs(effort): fix stale EffortPicker comment about xhigh normalization
openAIEffortToStandard is a type cast that passes 'xhigh' through as a
first-class EffortLevel — the shim only converts to 'max' at the
Anthropic request boundary, not here. Update the comment to match.
* docs(effort): update /effort help to match xhigh support matrix
The /effort --help output still described max as "Opus 4.6 only" and
xhigh as an "alias for max", but this PR promotes xhigh to a first-class
EffortLevel and allows it for OpenCode Claude Opus 4.7/4.8 (with max
also allowed for those Opus variants). Update the help so it matches
the picker/runtime behavior:
- max: "(Opus 4.6+)"
- xhigh: "(OpenAI/Codex and Opus 4.7+)"
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(sdk): address reviewer P2 — sync xhigh across override union, schemas, CLI
- Add 'xhigh_effort' to ModelCapabilityOverride union so the new
call at effort.ts:93 typechecks (P2 finding 1).
- Add 'xhigh' to AgentDefinition.effort enum (coreSchemas.ts) and
control.applied.effort enum (controlSchemas.ts), then regenerate
coreTypes.generated.ts so the SDK public contract matches the
first-class effort level (P2 finding 2).
- Add 'xhigh' to the --effort CLI flag allowed list and help text
(main.tsx:945-951) so users can actually pass --effort xhigh
instead of hitting "It must be one of: low, medium, high, max".
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(effort): narrow allowlist to shim-serialized models; sync max description
Address reviewer findings on PR #1505:
P2: The broad `m.includes('opus-4') || m.includes('sonnet-4')` branch
made older variants (claude-opus-4-1, claude-sonnet-4-5) advertise
effort support, but the Anthropic /messages shim only serializes
low/medium as anthropicBody.effort for the isAdaptive || isOpus45
set (opus-4-5/4-6/4-7/4-8, sonnet-4-6). For other models the shim
only emits thinking for high/max, so low/medium on those models
was silently dropped on the wire. Collapse the two 4-model branches
into one that matches the shim's serialization set; the substring
match still covers prefix variations (claude-, opencode-claude-).
P3: getEffortLevelDescription('max') said "Opus 4.6 only" but
modelSupportsMaxEffort now allows opus-4-6, opus-4-7, opus-4-8.
Update the shared description to "Opus 4.6+" so the picker and
/effort confirmation agree with the new support matrix (matching
the /effort --help text from
|
||
 JoneSSLandGitHub
|
07c1c56b4f |
Add Azure / Foundry launch support to VS Code extension (#1365)
* Enhance OpenClaude VS Code extension with Microsoft Foundry / Azure OpenAI support. Added configuration options for Azure API key, endpoint, and deployment settings. Updated README and documentation for new features, including a setup wizard for Azure integration. Improved terminal launch environment handling for Azure compatibility. * Fix packaged Windows helper runtime references * Use installed CLI from Windows helper aliases * Scope Windows helper env overrides to invocation * Align Windows alias docs with shipped helper |
||
 chioarubandGitHub
|
169d0f737d |
Add provider-profile model picker modes (#1472)
* fix(model): preserve discovered models for active profiles * test: isolate attribution settings state * fix(model): add provider profile picker modes * docs: document provider profile model picker mode * Preserve cached legacy model options on empty refresh |
||
|
JATMNandGitHub
|
3be54de16b |
Make OpenGateway the default startup provider (#1493)
Default fresh installs to the Gitlawb OpenGateway profile, keep validation behavior for saved profiles, and mark OpenGateway as the recommended provider in the picker. Update setup docs and generated integration metadata to reflect the API-key-backed OpenGateway route, and add coverage for the fresh-install startup environment. |
||
|
chioarubandGitHub
|
f3d41c6161 |
fix(release): verify npm latest tag and document @latest install (#1378)
* fix(release): verify npm latest tag and document @latest install * fix(auto-updater): use @latest for global installs |
||
|
|
5a22d604f8 |
feat(provider): add OpenCode Zen/Go subscription support (#1350)
* feat(provider): add OpenCode Zen/Go subscription support Add OpenCode as a first-class provider, enabling users to connect their Zen (pay-as-you-go) and Go ($10/mo) subscriptions via the /provider command. New integration descriptors: - vendors/opencode.ts — OpenCode Zen vendor (41 models) - gateways/opencode-go.ts — OpenCode Go gateway (12 models) - brands/opencode.ts — brand descriptor - models/opencode.ts — full model catalog (GPT, Claude, Gemini, Qwen, GLM, Kimi, MiniMax, Grok, DeepSeek, MiMo, Nemotron) Modified files: - integrationArtifacts.generated.ts — register descriptors and presets - providerProfile.ts — add OPENCODE_API_KEY env/secret key, 'opencode' profile type, and buildLaunchEnv handler - providerConfig.ts — add DEFAULT_OPENCODE_BASE_URL constants Auth: OPENCODE_API_KEY env var or interactive key entry in /provider Transport: openai-compatible (chat_completions) Base URLs: https://opencode.ai/zen/v1 (Zen), /zen/go/v1 (Go) * feat(provider): add [Zen]/[Go] tags to OpenCode preset labels Add visual tags in the /provider preset selection to distinguish OpenCode Zen (pay-as-you-go) from OpenCode Go (subscription). * feat(provider): enable dynamic model discovery for OpenCode Switch OpenCode vendor and Go gateway from static to hybrid model catalog with openai-compatible discovery. Models are fetched from /v1/models on startup and cached for 1 hour. Manual refresh is supported via the /provider UI. Static model list is preserved as fallback when discovery fails. * test(provider): add comprehensive OpenCode Zen/Go test suite 97 tests across 2 files covering: Integration tests (72 tests): - Vendor descriptor: id, label, classification, base URL, model, auth, transport, preset, validation, catalog, discovery, usage metadata - Gateway descriptor: id, label, vendorId, category, base URL, model, auth, transport, preset, catalog, discovery - Brand descriptor: id, label, canonicalVendorId, capabilities, modelIds - Model catalog: registration, vendor/gateway associations, required fields, valid classifications, reasoning/coding tags, no duplicates, model counts (41 Zen, 12 Go), modelDescriptorId consistency - Cross-reference: brand↔model, vendor↔model, gateway↔model, shared OPENCODE_API_KEY - Registry validation: no errors, no preset conflicts - Edge cases: unique ids, unique apiNames, non-empty labels, valid contextWindow/maxOutputTokens, valid defaultModel format, validation message content, discovery config Profile tests (25 tests): - Type guard: isProviderProfile('opencode'), rejects invalid values - buildLaunchEnv: persisted env, defaults, process env precedence, OPENCODE_API_KEY mapping, whitespace/null/undefined/empty handling, very long keys, special characters, concurrent access, boundary values, no credential leakage * fix(provider): add per-model endpoint routing (P1) Add endpointPath field to OpenAIShimTransportConfig so catalog entries can specify which API path to use per model. This addresses the maintainer's [P1] finding that all models were routed to /chat/completions regardless of their upstream endpoint. Changes: - descriptors.ts: add endpointPath?: string to OpenAIShimTransportConfig - openaiShim.ts: buildRequestUrl checks shimConfig.endpointPath first - vendors/opencode.ts: add transportOverrides to 31 catalog entries (GPT→/responses, Claude/Qwen→/messages, Gemini→/models/<id>) + switch to source: 'static' to prevent free models from live API - gateways/opencode-go.ts: add transportOverrides to 4 entries (MiniMax/Qwen→/messages) + switch to source: 'static' - opencode.test.ts: update tests for static source, remove discovery tests * refactor(opencode): model OpenCode Zen/Go as gateways (P2) * docs(provider): document OpenCode setup and move badge metadata to descriptors - Add OpenCode Zen/Go rows to README supported providers table - Add OpenCode Zen/Go examples and OPENCODE_API_KEY to advanced-setup.md - Add PresetBadge type to descriptor/manifest with badge propagation in artifact generator - Move 4 hard-coded preset badges ([FREE], [Sponsor], [Zen], [Go]) from ProviderManager.tsx into descriptor preset metadata - Add badge field to providerUiMetadata so UI components read from manifest - Update integration overview docs to recommend preset.badge for future gateways * fix(provider): match request body to endpoint format for OpenCode /messages and /responses (P1) Extend the openaiShim transport so that endpointPath overrides select both the URL and the correct body/response format: - /responses → OpenAI Responses API body (input, max_output_tokens) - /messages → Anthropic Messages API body (content blocks, system, max_tokens) Also fixes: abort listener leak in SSE passthrough, system prompt content-block flattening, and removes [Zen]/[Go] badge entries (P3). Co-Authored-By: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com> * fix(provider): add Google AI SDK body/response format for OpenCode Zen Gemini models (P1) The three Gemini models in the OpenCode Zen catalog (gemini-3.5-flash, gemini-3.1-pro, gemini-3-flash) were sending chat-completions body to the /models/gemini-* endpoint, which expects Google AI SDK format. - effectiveTransport now detects /models/gemini- endpointPath → 'gemini' - buildGeminiBody() converts Anthropic messages → Google contents[] with role mapping, systemInstruction, generationConfig, functionDeclarations - geminiSseToAnthropic() parses Google SSE frames → Anthropic stream events with text deltas, functionCall tool_use, finishReason mapping - _convertGeminiToAnthropicResponse() for non-streaming responses - Streaming/non-streaming routing via URL detection (/models/gemini-) - serializeBody(), hasToolsPayload, omitGeminiTools all updated * fix: prevent OpenCode model descriptors from shadowing canonical limits P1: Prefix all defaultModel values in opencode.ts with 'opencode-' so the fallback findModelDescriptorForApiName() doesn't match canonical model names. The OpenCode descriptors are still found via catalog entry lookup when the OpenCode route is active. P2: Add 'OpenCode Go' and 'OpenCode Zen' to PRESET_ORDER in ProviderManager.test.tsx between 'OpenAI' and 'OpenRouter' so navigateToPreset() sends the correct number of j keypresses. * fix: align OpenCode Go descriptor metadata with Zen - category: 'hosted' → 'aggregating' (both are aggregating gateways) - add validation block with OPENCODE_API_KEY guidance - update test assertion from 'hosted' to 'aggregating' * fix: accept OPENAI_API_KEY as fallback in OpenCode validation When users set up OpenCode Zen/Go via /provider, the key is saved as OPENAI_API_KEY (via buildCompatibilityProcessEnv). The validation block only checked OPENCODE_API_KEY, causing a startup warning even though the runtime auth header had the key it needed. Add OPENAI_API_KEY to validation.credentialEnvVars for both gateways, matching the pattern used by Hicap and Gitlawb Opengateway. * chore: trigger mergeability recheck --------- Co-authored-by: Gravirei <gravirei@users.noreply.github.com> Co-authored-by: OpenClaude (mimo-v2.5-pro) <openclaude@gitlawb.com> |
||
 stamsamandGitHub
|
2e3f7467f9 |
docs(vertex): clarify Claude on Vertex setup (#1273)
* docs(vertex): clarify Claude on Vertex setup * docs(vertex): point region overrides at env utils * docs(vertex): use cli model selector |
||
|
|
d02c10b399 |
feat: configure API retry backoff (#370) (#1095)
* feat: configure API retry backoff Add OpenClaude-branded retry controls for retryable API failures. - Replace the old CLAUDE_CODE_MAX_RETRIES config with OPENCLAUDE_MAX_RETRIES - Allow OPENCLAUDE_MAX_RETRIES=0 to disable retries after the initial request - Cap retry attempts at 100 and invalid values fall back to the default of 10 - Add OPENCLAUDE_RETRY_DELAY_MS to configure the exponential backoff base for APIs that omit Retry-After - Keep Retry-After precedence over configured retry delay - Document both settings in .env.example and advanced setup docs - Add focused retry configuration tests for defaults, invalid values, caps, zero retries, configured delay, and Retry-After precedence Validation: - bun test src/services/api/withRetry.test.ts - bun run build * Honor legacy max retries env var Add compatibility fallback from CLAUDE_CODE_MAX_RETRIES when OPENCLAUDE_MAX_RETRIES is unset. Document the deprecated fallback and cover precedence behavior in retry configuration tests. --------- Co-authored-by: JATMN <12479882+jatmn@users.noreply.github.com> |
||
|
Kevin CodexandGitHub
|
13a090162f | fix(gemini): preserve tool calls through opengateway (#1204) | ||
|
|
4d04f5bf4f |
feat(opengateway): add Gemini 3.1 Flash Lite + GLM 5.1 FP8 to catalog (#1194)
* feat(opengateway): add Gemini 3.1 Flash Lite + GLM 5.1 FP8 to catalog Opengateway now routes non-Xiaomi models through GMI Cloud (configured in opengateway/src/providers.ts via modelIds: - google/gemini-3.1-flash-lite-preview - zai-org/GLM-5.1-FP8 Adding both as catalog entries on the gitlawb-opengateway gateway descriptor so openclaude users see them in the model picker when the Opengateway preset is active. Each catalog entry reuses the existing upstream model descriptor (`gemini-3.1-flash-lite-preview`, `GLM-5.1`) for capability metadata; the apiName uses the full vendor-prefixed form the gateway routes on. No new model/brand/vendor descriptors needed — only the gateway catalog gets the new IDs. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * update opengateway --------- Co-authored-by: OpenClaude <openclaude@gitlawb.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
JATMNandGitHub
|
94e8ff3941 |
chore: centralize Bun version and refresh CI tool pins (#1171)
* chore: centralize Bun version and refresh CI tool pins - add .bun-version as the shared Bun source of truth for workflows and Docker builds - update PR and release workflows to read Bun from bun-version-file - refresh pinned GitHub Actions and Docker action SHAs to newer low-risk releases - align contributor docs with Bun 1.3.13 guidance * test: stabilize reset and provider profile persistence Harden knowledge graph reset behavior across Windows file-lock scenarios by improving SQLite and JSON reset signaling, preserving a safe JSON source of truth when SQLite cannot be cleared, and adding direct storage regression coverage. Also centralize deterministic config-home handling for tests, tighten provider profile persistence path resolution and cleanup semantics, isolate environment-sensitive suites with the env mutex, and remove flaky external npx dependency from the SDK consumer type test. * test: fix Codex OAuth callback flake Investigate the real provider smoke failure from GitHub Actions and fix the root cause instead of patching the symptom. - make Codex OAuth callback host explicit and consistent across redirect URI generation and listener binding - allow safe loopback host overrides for localhost, 127.0.0.1, and ::1 - harden Codex OAuth tests with env/fetch isolation so they do not poison neighboring provider suites - pin the OAuth callback tests to 127.0.0.1 to avoid localhost IPv4/IPv6 family mismatch flakes in CI Validated with bun test src/services/api/codexOAuth.test.ts, bun test src/services/api/providerConfig.codexSecureStorage.test.ts, and bun run test:provider. * test: harden Codex OAuth callback tests Investigate the recurring provider-smoke OAuth failures across multiple PR runs and fix the flaky callback test design at the root. - remove the free-port reservation race from Codex OAuth tests - add bounded callback retry only for loopback listener warm-up during the in-process OAuth test flow - move ephemeral callback port support into an explicit CodexOAuthService test seam instead of widening production env parsing - keep runtime callback-port semantics unchanged while adding regression coverage for callback host and port parsing Validated with targeted Codex OAuth tests and repeated provider-bucket reruns to check for recurring flake. * test: serialize provider shared-state suites Fix the recurring provider smoke flake at the root cause by serializing test suites that mutate process.env or globalThis.fetch. Add a shared test mutation lock and wire it into the provider bucket so Codex OAuth no longer races with unrelated provider/config/openai shim tests under Bun's parallel test execution. Cleanup now releases the lock in finally blocks, and the shared lock waits indefinitely by default to avoid timeout-based CI flakes. * test: fix smoke root causes and noisy suites Replace the Codex OAuth test's live loopback listener dependency with an injected listener seam, avoid module-mock leakage across provider suites, and clean up the auth-code listener test setup. Also harden noisy storage and search tests by asserting expected log output, isolating SQLite masterpiece persistence per test cwd, and removing routine benchmark/stress logging from passing runs. * build: harden Bun version install in Docker Validate the repo-tracked .bun-version value before using it in the Docker build stage, strip line endings, and install Bun through a quoted semver-only variable instead of raw shell expansion. * test: replace flaky conversation arc benchmark Fix the recurring smoke failure caused by an absolute wall-clock assertion in the normal unit suite. Replace the CI-speed-sensitive conversation arc benchmark with deterministic regression coverage that verifies repeated fact extraction, expected entity shapes, bounded graph growth, and populated-summary behavior. * test: isolate shared-state smoke suites * test: restore codex credential mocks between suites * test: fix shared-state and provider init-order flakes * test: isolate remaining shared-state smoke suites Serialize the remaining smoke-sensitive suites that mutate process env, CLAUDE_CONFIG_DIR, fetch, or SDK session globals. Add shared lock coverage to discovery, agent/skills loading, platform storage, and SDK lifecycle/preserved-segment tests. Restore session and cwd state inside the lock boundary so parallel files cannot leak bootstrap state into knowledge graph and SDK isolation tests. Validated with repeated smoke and full-suite passes: - bun run smoke (2x) - bun test - bun test --max-concurrency=1 - bun run test:provider - python -m pytest -q python/tests - npm run test:provider-recommendation |
||
|
0xfandomandGitHub
|
b8c9d90703 |
docs(ollama): drop ollama launch openclaude instructions (#1163)
The `ollama launch openclaude` syntax in README and advanced-setup.md was docs-only (added in #716), gated on the companion ollama/ollama#15618 integration that has not landed upstream. Users following these instructions get `Error: unknown integration: openclaude` (issue #744 originally, #1134 now). Remove the misleading section + table mention so the env-var setup above remains the documented path. Can be re-added once the upstream ollama integration ships. Closes #1134 |
||
|
|
18483e4d96 |
feat(provider): add Xiaomi MiMo integration (#1152)
* feat(provider): add Xiaomi MiMo integration Add Xiaomi MiMo as an official OpenAI-compatible provider with provider-profile persistence, env-only detection, and sponsor labeling in the provider picker. Co-Authored-By: OpenClaude (zai-org-glm-5-1) <openclaude@gitlawb.com> * feat(provider): rebase Xiaomi MiMo as top-level provider Promote Xiaomi MiMo from generic OpenAI-compatible shim route to a first-class top-level provider matching the MiniMax pattern. Includes brand/model descriptors, env-only detection, provider auto-detect, status labels, legacy provider type, model picker, and profile env persistence. Co-Authored-By: OpenClaude (zai-org-glm-5-1) <openclaude@gitlawb.com> * Fix Xiaomi MiMo provider integration Promote Xiaomi MiMo as a first-tier OpenAI-compatible vendor and align its descriptor with the integration guide. Use the resolving Xiaomi MiMo API host while normalizing the stale docs host alias, wire Xiaomi catalog options into /model, and ensure model selection/display uses OPENAI_MODEL for Xiaomi instead of Claude defaults. Update provider profile/startup handling, OpenAI shim detection, docs, generated integration artifacts, and focused regression tests. Verification: bun run integrations:check; focused bun test provider/model suites; bun run build; bun run smoke. * Fix MiMo startup profile base URL normalization --------- Co-authored-by: OpenClaude (zai-org-glm-5-1) <openclaude@gitlawb.com> Co-authored-by: JATMN <the@jat.mn> |
||
 jackil182andGitHub
|
41b2496101 |
docs: update setup guides to clarify the only available auth method for Gemini (#1064)
* Update README.md Access token and local ADC workflow authentication is NOT available for Gemini. * Update advanced-setup.md API key authentication is the only available method for Gemini |
||
 TechBrewBossandGitHub
|
f5ec185609 | Store provider profiles in user config (#969) | ||
|
JATMNandGitHub
|
6d0953a79c | fix(groq): strip unsupported store field (#983) | ||
|
|
b471745fb1 |
Registry-Based Integration Architecture for Providers, Gateways, and Models (#910)
* setting up
* updated plan with missing notes for discovery cache
* build out inital checklist and planning adjustments
* Phase 1A-1D
* Fix descriptor-backed provider profile routing
- preserve GitHub, Bedrock, and Vertex runtime flags during profile activation\n- serialize descriptor-backed startup profiles into legacy-compatible persisted kinds\n- add regression coverage for activation, restart round-trip, and saved-profile switching\n- guard integration registration so repeated imports stay idempotent in tests
* feat: finish phase 1 provider descriptor routing
Complete the Phase 1E CLI/usage migration work and the Phase 1F verification pass for descriptor-backed providers.
Details:
- derive valid --provider values from descriptor registry and compatibility mappings instead of a fixed list
- preserve special CLI semantics for ollama and minimax while allowing descriptor-backed OpenAI-compatible routes such as deepseek and openrouter to pick up descriptor base URLs
- add getUsageDescriptor() so /usage resolves vendor/gateway metadata and follows usage delegation
- switch Settings Usage rendering to descriptor-backed usage resolution for Anthropic, MiniMax, and neutral unsupported fallbacks
- make integration loading idempotent via ensureIntegrationsLoaded() so registry-backed helpers survive tests that clear the registry
- fix compatibility mapping for mistral so the preset routes through vendorId=openai with gatewayId=mistral rather than a nonexistent direct vendor route
- harden provider profile and startup tests so descriptor-backed providers, legacy OpenAI startup files, and unknown stored providers round-trip correctly
- remove a stale ollama model mock that was leaking across the full model test suite
- update plan/progress.md with the current 1E complete / 1F in-progress verification state and the note that repo-wide typecheck failures are pre-existing outside this migration slice
Verification:
- bun test src/commands/usage/index.test.ts src/integrations/compatibility.test.ts src/utils/providerFlag.test.ts src/utils/providerProfiles.test.ts src/utils/providerProfile.test.ts src/utils/model/modelCache.test.ts src/integrations/index.test.ts src/integrations/registry.test.ts
- filtered bun run typecheck output for the files changed in this branch is clean
* Phase 2 planning
* feat: complete phase 2A validation and discovery cache
* fix: address review findings for phase 2 cache and validation
Fixes the follow-up review issues from the Phase 2A / 2A.5 work.
Completed work:
- made discovery cache stale entries reachable through getCachedModels(..., { includeStale: true }) while keeping fresh-by-default behavior unchanged
- kept recordDiscoveryError stale-data preservation useful to later /model consumers by exposing stale and error-only entries through the public helper API
- extended descriptor-backed validation routing metadata with host alias matching support
- updated MiniMax validation routing to recognize both api.minimax.io and api.minimax.chat endpoints
- added regression coverage for stale cache reads, error-only cache entries, and MiniMax chat-host validation
- updated progress.md notes so the recorded 2A.5 helper behavior matches the implementation
* feat: complete phase 2B discovery and readiness migration
Implement descriptor-backed discovery and readiness routing for Phase 2B.
Highlights:
- add src/integrations/discoveryService.ts to execute declarative catalog.discovery configs with shared discovery-cache integration
- add hybrid merge behavior so curated descriptor catalog entries stay ahead of discovered duplicates
- add typed startup readiness metadata via ReadinessProbeKind and wire gateway descriptors for ollama, atomic-chat, lmstudio, and openrouter
- export probeOllamaModelCatalog() so discovery can distinguish unreachable Ollama from reachable-but-empty catalogs
- migrate ProviderManager and /provider flows to probeRouteReadiness() while preserving existing Ollama messaging
- route bootstrap local model discovery through descriptor-backed discovery for recognized local routes, while keeping legacy fallback for generic custom endpoints
- add resolveDiscoveryRouteIdFromBaseUrl() so bootstrap can share descriptor-backed discovery and local provider labels
- preserve explicit provider env precedence during applySavedProfileToCurrentSession() after focused verification exposed the regression
- update plan/progress.md to mark Phase 2B complete and record the verification notes
Verification:
- bun test src/integrations/discoveryService.test.ts
- bun test src/components/ProviderManager.test.tsx
- bun test src/commands/provider/provider.test.tsx
- bun test src/utils/providerDiscovery.test.ts src/integrations/registry.test.ts src/integrations/index.test.ts
- filtered bun run typecheck for the touched 2B files returned FILTER_CLEAN
* feat: complete phase 2c provider metadata migration
Finish the Phase 2C runtime metadata adoption work on cheeky-cooking-moon.
Provider UI metadata:
- add shared route metadata and provider preset UI metadata helpers
- move preset labels/defaults, route type labels, and custom-header capability checks onto descriptor-backed lookups
- update ProviderManager and /provider summaries/setup copy to read shared descriptor metadata instead of bespoke switches
- extend local gateway descriptors with default model metadata used by the shared UI helpers
Model discovery UX:
- add route catalog option builders for descriptor-backed /model rendering
- update /model to resolve the active route, read cached route catalogs before rendering, and trigger background refresh when cached discovery is stale
- add /model refresh plus in-picker refresh via modelPicker:refresh and the r keybinding
- clear discovery cache on manual refresh and surface non-blocking loading/success/stale-error states in ModelPicker
- keep descriptor-backed dynamic and hybrid routes on the shared discovery cache service
Verification and hardening:
- fix combined test pollution by isolating /model test module imports and using real OpenRouter descriptor metadata during shared runs
- update progress.md to mark Phase 2C complete with verification notes
- verified with bun test for provider profiles, ProviderManager, /provider, /model, discovery cache, and provider validation suites
* feat: complete phase 2d runtime provider alignment
Align descriptor-backed runtime provider behavior with the legacy APIProvider surface so active routes, OpenAI shim behavior, and resume handling all resolve through the same metadata path.
Add runtimeMetadata.ts to centralize active route detection, OpenAI shim overrides, and native-format inference. Update provider resolution to map descriptor-backed routes onto legacy provider categories while preserving existing compatibility fallbacks for Foundry, NVIDIA NIM, MiniMax, GitHub, Bedrock, and Vertex.
Move request-shaping rules onto descriptor metadata for DeepSeek, Moonshot, Kimi Code, Gemini, Mistral, GitHub, and local gateways, including reasoning_content preservation, deepseek-compatible thinking payloads, max_tokens field selection, and store field stripping. Treat GitHub Claude native transport as Anthropic-native during conversation recovery so thinking blocks survive resume flows.
Extend focused tests for provider resolution, OpenAI shim request shaping, and conversation recovery, and update phase tracking notes in progress.md to mark 2D complete with verification details.
* feat: complete phase 2e drift audit
Complete the Phase 2E verification and drift-audit packet for the descriptor migration branch.
Add representative provider-summary coverage for descriptor-backed OpenRouter routing plus Gemini and Mistral current-provider summaries in src/commands/provider/provider.test.tsx. Extend ProviderManager coverage with first-run Atomic Chat discovery-backed setup and a regression test proving the set-active picker now uses descriptor-backed provider-type labels.
Replace stale saved-profile picker wording in ProviderManager so saved profiles no longer collapse to a coarse anthropic/openai-compatible split and instead render the route's descriptor-backed provider type label.
Add plan/phase-2e-drift-audit.md documenting the remaining intentional switch sites and non-switch provider branches across provider summaries, active-route detection, OpenAI shim env remapping, auth/header exceptions, and conversation recovery. Update plan/progress.md to mark Phase 2 and 2E complete on-branch, record focused verification, and note the follow-up hardening completed during audit review.
Verification completed during this packet: bun test src/components/ProviderManager.test.tsx src/commands/provider/provider.test.tsx src/utils/providerValidation.test.ts src/integrations/discoveryService.test.ts src/commands/model/model.test.tsx and bun test src/utils/providerDiscovery.test.ts src/utils/model/providers.test.ts src/services/api/openaiShim.test.ts src/utils/conversationRecovery.test.ts. Filtered typecheck output still shows pre-existing baseline noise in src/services/api/openaiShim.ts and src/utils/conversationRecovery.ts only.
* fix: close phase 2 provider parity follow-through
Complete the skipped provider-surface follow-up discovered during the post-Phase-2 review.
- add focused status coverage for NVIDIA NIM and MiniMax sessions
- add Mistral entries to legacy teammate/model compatibility configs
- fill deprecation placeholders for the widened APIProvider surface
- add focused regression tests for status and teammate fallbacks
- update the Phase 2 drift audit and progress tracker with the compatibility-bridge notes and Phase 3 staging context
* phase 3 planning
* refactor: start phase 3a dead-switch cleanup
Begin the Phase 3 cleanup pass with the metadata-only dead-switch removals that are safe to land independently on cheeky-cooking-moon.
Completed work:
- updated plan/progress.md to move Phase 3 and Phase 3A into IN_PROGRESS, added slice-level checklists, and recorded what remains intentionally deferred to later packets
- removed duplicated OpenAI-compatible status-display branches in src/utils/status.tsx by routing openai/codex/nvidia-nim/minimax through shared metadata helpers
- replaced the pure transport-kind label switch in src/integrations/routeMetadata.ts with shared label metadata
- replaced the pure provider-label switch in src/components/CostThresholdDialog.tsx with a shared provider-label map
- added focused regression coverage in src/utils/status.test.ts, src/integrations/routeMetadata.test.ts, and src/components/CostThresholdDialog.test.ts
Verification:
- bun test src/utils/status.test.ts src/utils/swarm/teammateModel.test.ts src/utils/model/providers.test.ts
- bun test src/integrations/routeMetadata.test.ts src/utils/status.test.ts src/components/CostThresholdDialog.test.ts src/utils/model/providers.test.ts
- filtered bun run typecheck for the touched status/routeMetadata/CostThresholdDialog files returned FILTER_CLEAN
* refactor: complete phase 3b and 3c cleanup
Complete the uncommitted Phase 3B compatibility rename work and the Phase 3C env-shaping consolidation on cheeky-cooking-moon.
Phase 3B:
- introduce LegacyAPIProvider while keeping APIProvider as the public compatibility alias
- introduce LegacyProviderModelConfig and LEGACY_PROVIDER_MODEL_CONFIGS while keeping ModelConfig and ALL_MODEL_CONFIGS as compatibility exports
- switch modelStrings, deprecation helpers, and provider profile compatibility naming onto the legacy/compatibility terminology
Phase 3C:
- add shared managed-env clear/apply helpers in providerProfile.ts and route buildLaunchEnv through the shared compatibility env shaper
- route applyProviderProfileToProcessEnv through the same compatibility env shaper so config-backed profiles and startup/session env construction stay aligned
- preserve explicit exception behavior for github, mistral, bedrock, vertex, bankr aliasing, MiniMax fallback detection, and NVIDIA NIM mode markers
- reduce createOpenAIShimClient to the remaining credential alias hydration that resolveProviderRequest does not already cover
- fix applySavedProfileToCurrentSession so saved-profile switching can move away from stale GitHub env selections
- add regression coverage for NVIDIA NIM env stamping and stale Codex-managed env clearing
- update progress.md to mark Phase 3B and 3C complete on branch and record the verification notes
Verification:
- bun test src/utils/model/providers.test.ts src/utils/providerProfiles.test.ts src/utils/swarm/teammateModel.test.ts src/utils/status.test.ts
- bun test src/utils/providerProfile.test.ts src/utils/providerProfiles.test.ts src/services/api/openaiShim.test.ts
- filtered bun run typecheck confirmed no new hits in providerProfile.ts or providerProfiles.ts; remaining openaiShim.ts hits are existing repo baseline debt
* docs: complete phase 3d audit and architecture note
Complete the Phase 3D final audit/documentation packet on cheeky-cooking-moon.
Work completed:
- add plan/phase-3d-final-audit.md with the final post-Phase-3 inventory of remaining provider-specific runtime branches
- classify the remaining exceptions as intentional long-term runtime differences or temporary env/config compatibility bridges
- confirm the audit did not uncover new missed runtime migration work that requires additional Phase 3 code changes
- add docs/architecture/integrations.md to document the descriptor-first architecture, current constraints, known exceptions, and follow-on guidance for future cleanup
- update plan/progress.md to mark Phase 3D complete on branch, mark 3C merged on branch, and point the tracker at Phase 4A next
Key exception categories documented:
- github dual-mode transport behavior
- mistral dedicated route/runtime shaping
- bedrock/vertex/foundry native Anthropic-family paths
- Azure and Bankr request-auth/header differences
- Gemini, DeepSeek, and Moonshot/Kimi OpenAI-shim quirks
- MiniMax dedicated usage handling
- native web-search gating
- env-only MiniMax and NVIDIA NIM compatibility fallbacks
- env/config compatibility bridges such as route detection, --provider shaping, and startup/provider summaries
Notes:
- this packet is branch-local audit/documentation work only; no runtime code paths were changed
- no new tests were required for the audit/doc pass
* docs: stage phase 4 tracker and codex profile guard
Add the Phase 4 documentation/reference-samples plan to progress.md in the same packet/checkpoint structure as earlier phases, and reconcile the Phase 3 tracker summary with the completed cleanup state. Also fix applySavedProfileToCurrentSession so Codex saved-profile activation does not overwrite an already explicit live provider selection, while still clearing stale profile-managed markers when needed.
* docs: complete phase 4a and 4b guides
Expand the integrations architecture note with descriptor authoring, routing-contract, transport-boundary, and compatibility-layer guidance. Add overview and glossary docs under docs/integrations/, plus new how-to guides for adding vendors and gateways with one-file and two-file patterns, discovery cache guidance, token-field guidance, and compatibility follow-through. Update progress.md to mark Phase 4 in progress, Phase 4A complete, and Phase 4B complete with notes about the new docs structure and guide outputs.
* docs: complete phase 4 integration docs
Add the remaining descriptor contributor guides for models, anthropic proxies, and /usage support.
Add a reference sample pack and a common-pitfalls checklist, update the integrations overview, and reconcile plan/progress.md so Phase 4 is marked complete on cheeky-cooking-moon with the current implementation boundaries called out explicitly.
* docs: reconcile tracker waivers and checkpoints
Update plan/progress.md to formally waive the remaining repo-wide typecheck item for Phase 1F as pre-existing debt outside the descriptor migration scope, and mark the Phase 4 branch-local checkpoints as landed on cheeky-cooking-moon with the corresponding commit references.
* Align Z.AI merge fallout with descriptors
Reviewed the upstream main merge against plan/cheeky-cooking-moon.md and removed drift from the old switch/helper-based Z.AI provider path.
Moved Z.AI reasoning, context-window, and max-output metadata into the descriptor route catalog so thinking support can read catalog capabilities instead of URL/model helper checks.
Removed the standalone src/utils/zaiProvider.ts helper and updated startup/provider-discovery labeling to resolve known direct routes through descriptor route metadata.
Simplified --provider handling for Z.AI by letting descriptor defaults provide the base URL and default model through the generic OpenAI-compatible provider branch.
Updated startup and provider-discovery tests for descriptor-backed labels, added Z.AI descriptor-label coverage, and documented the post-main-merge reconciliation in plan/progress.md.
Verification before commit: bun test src/utils/providerFlag.test.ts src/utils/providerProfiles.test.ts src/utils/thinking.test.ts src/components/StartupScreen.test.ts src/utils/providerDiscovery.test.ts; bun test src/integrations/compatibility.test.ts src/integrations/index.test.ts src/integrations/registry.test.ts src/services/api/openaiShim.test.ts; git diff --check.
* fix: restore descriptor migration behavior and isolate provider tests
Restore the descriptor-era Anthropic/OpenAI boundary during conversation recovery by threading the legacy provider category into usesAnthropicNativeMessageFormat instead of relying on ambient env-only route detection.
Harden branch-added provider-facing tests so they do not inherit leaked bun mock.module state from neighboring suites. Status, thinking, teammate fallback, and GitHub model options tests now restore mocks and/or import fresh modules under explicit provider context.
Update bugfix assertions to validate the descriptor-backed openaiShim contract for removeBodyFields/store stripping instead of the pre-refactor inline conditionals.
Validation:
- focused status/thinking/conversationRecovery/bugfix suites pass
- full bun test --max-concurrency=1 is down to the existing conversationArc perf benchmark failure only
- bun run smoke
- bun run build
- npm pack
* fix: close descriptor review drift and provider regressions
Address the follow-up review against plan/cheeky-cooking-moon.md by fixing the remaining runtime drift and locking the behavior with focused coverage.
Completed work:
- make NVIDIA NIM descriptor-backed auth consistent across validation, --provider env shaping, and openaiShim request auth so NVIDIA_API_KEY works without requiring OPENAI_API_KEY
- resolve /usage from the active descriptor route instead of collapsing most OpenAI-compatible providers into the legacy openai bucket
- honor discoveryRefreshMode in /model so manual, on-open, background-if-stale, and startup catalogs no longer behave identically
- clarify docs/progress notes so the branch no longer overstates one-file additive onboarding while loader and preset/UI compatibility surfaces are still manual
Verification:
- bun test src/services/api/openaiShim.test.ts src/utils/providerValidation.test.ts src/utils/providerFlag.test.ts src/utils/model/providers.test.ts src/commands/usage/index.test.ts src/commands/model/model.test.tsx
* docs(plan): require descriptor-native gateway onboarding closure
Investigated the current descriptor onboarding flow and documented the remaining manual choke points in the loader, preset compatibility mapping, provider UI metadata, and handwritten preset typing.
Tighten cheeky-cooking-moon so additive onboarding is a hard requirement, add Phase 3E for descriptor-native onboarding closure, and update the progress tracker to reflect that follow-up work instead of treating the branch as fully complete.
* feat(integrations): close descriptor-native onboarding
Implement the Phase 3E generated-artifact workflow for integration onboarding.
- add integration artifact generation and check scripts
- generate loader inventory, preset manifest, and preset type from descriptors
- move preset participation onto descriptor preset metadata for preset-facing vendors and gateways
- derive compatibility and provider UI metadata from the generated manifest
- remove descriptor-level preset ordering and sort presets by description with standard alphanumeric ordering
- pin the custom preset to the bottom automatically in generated ordering
- add validation for duplicate preset ids and incomplete preset metadata
- add generator tests for representative gateway and direct-vendor onboarding
- refresh ProviderManager tests for generated preset ordering
- update architecture/how-to/reference docs and progress tracking for the new regeneration workflow
* Fix provider profile and discovery drift
Honor route-specific auth env vars across descriptor-backed OpenAI-compatible routes by centralizing credential resolution and using it in validation, bootstrap, discovery, and the OpenAI shim.
Persist Anthropic startup fallbacks as native anthropic profiles and restore them correctly at startup so the legacy startup file stays aligned with the active provider.
Wire discoveryRefreshMode='startup' into startup and provider activation flows, with LM Studio as a live startup-refresh example, and add regression coverage for validation, startup env shaping, discovery refresh, and shim auth handling.
* Pin Anthropic provider preset to the top
Keep the existing custom gateway preset pinned to the bottom while moving the Anthropic preset ahead of the description-sorted remainder.
Regenerate the integration preset manifest/order and extend the artifact generator coverage to lock in both ordering rules.
Validation: bun test src/integrations/artifactGenerator.test.ts src/components/ConsoleOAuthFlow.test.tsx; bun run build
* docs: refresh integration and setup guides
Update the new descriptor-era integration docs so they read as current contributor guidance instead of rollout notes, and align the authoring examples with the actual runtime metadata flow.
Highlights:
- add a CONTRIBUTING.md pointer to the integration overview and focused how-to guides
- remove branch/phase-specific wording from the integration docs
- fix OpenAI-compatible header guidance to use transportConfig.openaiShim headers and custom-header flags
- clarify anthropic proxy onboarding around generated loader support
- refresh advanced setup with current Codex, Gemini, Mistral, and profile-launch details
- fix LiteLLM /provider instructions and clarify local no-auth behavior
- tighten quick-start and non-technical cross-links so users can find the advanced provider docs
* fix: close descriptor integration drift
Apply descriptor-backed static headers to OpenAI-compatible request execution and model discovery, preserving request-specific header precedence.
Allow Gemini profile launch with API key, access-token, or ADC credentials, and align Gemini fallback defaults with the descriptor/docs default model.
Add regression coverage for descriptor header propagation, Gemini defaults, and discovery auth/header behavior.
* post-phase follow-up task added
* Fix xAI merge follow-ups
Route env-only XAI_API_KEY sessions through the OpenAI-compatible shim using descriptor-backed xAI defaults, and map the xAI key into OPENAI_API_KEY for shim auth.
Hydrate legacy profile: xai startup env with xAI descriptor defaults, preserving XAI_API_KEY and OpenAI-compatible launch behavior.
Update progress tracking for post-merge xAI descriptor inventory and clarify that profile-owned custom headers remain open despite adjacent auth/static-header plumbing.
Add regression coverage for env-only xAI client routing, legacy xAI launch env, shell key precedence, and the Gemini/OpenAI client test isolation issue.
* Complete profile custom headers follow-up
Add persisted provider-profile customHeaders support with shared parsing and sanitization for compact Name: value input. Reject malformed and reserved auth/internal headers before saving or applying profile-owned headers.
Expose a descriptor-gated /provider custom headers step, preserve headers during profile edit/update, and apply supported profile headers through ANTHROPIC_CUSTOM_HEADERS for active env and startup fallback profiles.
Propagate profile headers into descriptor discovery refresh and bootstrap model discovery while preserving descriptor/profile/auth merge order. Add focused regression coverage and mark the progress tracker packet complete.
* Allow api-key custom provider headers
Permit api-key in /provider custom header input and preserve it when OpenAI-compatible shim requests are built. This is intentional for gateway providers that require an api-key header in addition to, or instead of, standard bearer auth.
Keep managed credential headers protected by continuing to reject/strip authorization and x-api-key, plus Anthropic/Claude-owned headers. Add parser, profile env, and outgoing request coverage for the intended behavior.
* fix: restore API mode picker for OpenAI-compatible profiles
Use descriptor transport metadata instead of the legacy provider id when deciding whether provider profiles support OpenAI-compatible options. This restores the Chat Completions vs Responses picker for the Custom OpenAI-compatible preset after it moved to the descriptor-backed custom route.
Preserve apiFormat and custom auth header profile fields for all routes whose transportConfig.kind is openai-compatible, so selecting Responses is saved and applied as OPENAI_API_FORMAT=responses.
Tests: bun test src/components/ProviderManager.test.tsx; bun test src/utils/providerProfiles.test.ts; bun run build; bun run smoke
* fix: respect explicit provider routing with xAI env
Ensure env-only XAI_API_KEY fallback does not take over when Bedrock, Vertex, or Foundry has been explicitly selected. This preserves native transport routing while still allowing bare xAI env setup to use the OpenAI-compatible shim.
Restore api-key to the managed custom-header blocklist now that /provider exposes the API mode/auth-header controls for OpenAI-compatible profiles. The shim and provider override paths strip api-key again, while OPENAI_AUTH_HEADER=api-key remains available for explicit auth configuration.
Tests: bun test src/services/api/client.test.ts src/utils/providerCustomHeaders.test.ts src/utils/providerProfiles.test.ts src/services/api/openaiShim.test.ts; bun run build; bun run integrations:check; bun run smoke
* docs: fix integration drift
Align integration and setup docs with the current implementation.
- show model descriptor examples as array default exports, matching the generated MODEL_DESCRIPTOR_GROUPS loader contract
- document provider-scoped model env vars instead of implying OPENAI_MODEL globally overrides ANTHROPIC_MODEL
- clarify generated provider preset ordering: anthropic first, custom last, description-sorted middle entries
- update LiteLLM examples and /provider guidance to use the /v1 OpenAI-compatible base URL
Verification: bun run integrations:check
* Fix provider discovery cache isolation
* Stabilize provider env tests
* Stabilize provider test isolation
Completed work:
- Isolated GitHub model option tests from cached availableModels settings.
- Isolated startup discovery tests from live process.env provider flag races.
- Mocked teammate provider fallback tests at the provider helper boundary.
- Moved cost threshold provider labels into a pure helper for deterministic tests while preserving runtime active-provider behavior.
Validation:
- bun test src/components/CostThresholdDialog.test.ts src/integrations/discoveryService.test.ts src/utils/model src/utils/swarm
- bun run build
- bun run smoke
* test: isolate startup screen model settings
Clear the session settings cache and persisted global model around StartupScreen provider-detection tests.
This prevents earlier provider/model suites from leaking saved non-Anthropic models into the default Anthropic startup assertions.
Verified with: bun test src/components/StartupScreen.test.ts src/integrations/discoveryService.test.ts src/utils/model/modelOptions.github.test.ts
Full bun test now only fails the unrelated Conversation Arc sub-millisecond performance benchmark.
* test: isolate route discovery and github model options
Restore Bun module mocks around discoveryService tests before loading fresh route-discovery modules.
Pin the GitHub model-options test to a complete providers.js mock so cached provider mocks from other suites cannot hide Copilot options.
Verified with: bun test src/integrations/discoveryService.test.ts src/utils/model/modelOptions.github.test.ts
Also ran full bun test; only the unrelated Conversation Arc sub-millisecond performance benchmark fails locally.
* test: avoid startup discovery cache collision
Use the 127.0.0.1 LM Studio alias in refreshStartupDiscoveryForActiveRoute so it still resolves the active route from env but does not share the cache partition with the preceding startup refresh test.
This keeps the assertion on network refresh stable under Bun 1.3.11 serialized runs.
Verified with: bun test --max-concurrency=1 src/integrations/discoveryService.test.ts src/utils/model/modelOptions.github.test.ts
Also ran full bun test --max-concurrency=1; only the unrelated Conversation Arc perf benchmark fails locally.
* fix: isolate OpenAI-compatible route credentials
Restrict OpenAI-compatible shim auth to provider overrides, resolved route credentials, or explicit OPENAI_API_KEY instead of ambient provider-specific secrets.
Remove NVIDIA and Bankr compatibility fallbacks that could promote provider-specific API keys into unrelated OpenAI-compatible routes. Preserve Bankr base URL/model compatibility before route credential resolution so Bankr still resolves through descriptor credentials.
Clear stale NVIDIA_NIM and copied OPENAI_API_KEY values when switching away from NVIDIA NIM, Bankr, or xAI provider flags to avoid carrying provider secrets across route boundaries.
Add regressions for stale NVIDIA, MiniMax, and Bankr keys not leaking into OpenRouter-style routes, plus provider-flag cleanup for copied NVIDIA/Bankr/xAI keys.
Validation: bun test src/services/api/openaiShim.test.ts; bun test src/utils/providerFlag.test.ts; bun run build; bun run smoke.
* fix: guard model discovery privacy paths
Suppress descriptor and legacy model discovery while essential-only traffic mode is active.
Use the partitioned discovery cache key for /model cache reads, stale checks, and manual refresh clears, including route-specific credentials and custom headers.
Partition legacy local OpenAI additional model caches by credentials and routing headers to avoid catalog reuse across profiles.
Add coverage for OpenRouter route credentials, descriptor privacy suppression, legacy discovery privacy suppression, and local cache scope partitioning.
* Fix artifact checks and knowledge graph persistence
Normalize generated integration artifact comparisons so Windows line endings do not make checked-in artifacts appear stale.
Skip knowledge graph entity persistence when re-adding an existing entity with identical attributes, avoiding repeated disk writes during automatic fact extraction and restoring the conversation arc performance benchmark.
Verified with bun test src/integrations/artifactGenerator.test.ts --max-concurrency=1, bun test src/utils/conversationArc.perf.test.ts --max-concurrency=1, and bun test --max-concurrency=1.
* test: isolate privacy discovery cache path
The descriptor discovery privacy test could observe stale OpenRouter cache data populated by an earlier test and receive source=stale-cache instead of static. Use a test-specific API key so the privacy assertion gets its own discovery cache partition while still verifying that nonessential traffic disables network discovery.
Verified with bun test src/integrations/discoveryService.test.ts --max-concurrency=1 and bun test --max-concurrency=1.
* test: accept cached privacy discovery result
* test: set privacy gate before discovery import
* test: prevent discovery privacy mock bleed
Guard descriptor model discovery directly on CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC so nonessential traffic stays disabled even if the privacyLevel module is mocked in-process.
Reduce broad fastMode test mocks for shared modules and use real state/config test hooks, preventing Bun module mock namespaces from leaking into discovery and /model tests.
Verified with bun test src/utils/fastMode.test.ts src/utils/model/openaiModelDiscovery.test.ts src/integrations/discoveryService.test.ts src/commands/model/model.test.tsx --max-concurrency=1 and bun test --max-concurrency=1.
* test: prevent discovery privacy mock bleed
Add an env-level fallback guard to descriptor model discovery so disabled nonessential traffic cannot be bypassed by stale mocked privacy helpers.
Tighten the fastMode regression tests by setting real bootstrap/config state only after the tested module is imported, avoiding broad module mocks that can leak into unrelated discovery tests or behave differently under Bun in CI.
Verified with focused discovery/fastMode/model suites and the full serial bun test suite.
* fix: harden fast mode test isolation
Ignore non-string GrowthBook values when resolving the fast mode unavailable reason so boolean flag payloads cannot surface as false.
Make the affected regression tests install explicit provider mocks for their own scenarios and reset env state, preventing stale provider mocks from changing fastMode and conversation recovery behavior across the serial Bun test run.
* test: harden fast mode module mocks
Expand the fastMode GrowthBook and provider test mocks so later imports in the same Bun test process can resolve the named exports they expect. This prevents order-sensitive failures when model command tests run after fast mode tests.\n\nVerified with: bun test --max-concurrency=1
* feat: consolidate integration runtime metadata
Move OpenAI-compatible model runtime limits into descriptor-backed brand and model metadata, adding Gemini, GLM, MiniMax, Mistral, Nemotron, xAI, and OpenAI-compatible alias descriptor groups. Update generated integration artifacts, route catalog option handling, thinking capability lookup, and docs to use modelDescriptorId-backed runtime metadata.
Split OpenAI shim capability flags into supportsApiFormatSelection and supportsAuthHeaders, and update provider profile sanitization, ProviderManager forms, descriptor validation, and integration authoring docs so fixed routes do not preserve unsupported API format or auth-header settings.
Harden env-only MiniMax and xAI routing. Resolve shared route intent before client setup, reject conflicting OpenAI base URLs, preserve provider-specific base overrides, sanitize stale OpenAI shim knobs, copy provider credentials intentionally, and keep legacy provider labels, context windows, max output limits, model lists, and provider switching aligned.
Refresh MiniMax defaults and catalog entries, add descriptor-backed runtime limits for migrated models, preserve external OpenAI limit overrides, and add regression coverage for env-only MiniMax/xAI, provider-profile capability stripping, route catalog options, copied credential cleanup, and context/runtime limit detection.
Verification performed: bun test src/utils/providerFlag.test.ts; bun test src/services/api/client.test.ts src/utils/model/providers.test.ts src/integrations/routeMetadata.test.ts; bun test src/utils/context.test.ts src/utils/thinking.test.ts src/services/compact/autoCompact.test.ts; bun test src/integrations/routeMetadata.test.ts src/services/api/client.test.ts src/utils/model/providers.test.ts src/utils/providerValidation.test.ts src/integrations/index.test.ts src/utils/status.test.ts; bun run build; bun run smoke.
* test: isolate provider env in conversation recovery
Snapshot and restore all provider-selection environment variables used by the GitHub native Claude resume test instead of only restoring the GitHub flag and OPENAI_MODEL.
The full single-concurrency suite exposed that earlier tests can leave higher-priority provider flags in process.env, causing deserializeMessages to resolve a non-GitHub provider and strip thinking blocks even though the test intended to exercise GitHub native Claude transport.
The test now clears provider routing env before setting CLAUDE_CODE_USE_GITHUB=1 and OPENAI_MODEL=claude-sonnet-4-6, then restores the original env values in afterEach.
Verification: bun test src/utils/conversationRecovery.test.ts; bun test --max-concurrency=1.
* test: isolate conversation recovery provider state
* test: pin conversation recovery provider mock
* test: isolate knowledge graph persistence
* fix: make knowledge graph reset synchronous
* test: restore integration registry after unit tests
* remove plans dir
* delete plans
* Fix provider routing test failures
Restore the missing first-party Anthropic auth routing imports used by getAnthropicClient so OpenAI-compatible provider client creation no longer throws at runtime.
Keep GitHub provider resolution from inheriting OPENAI_API_FORMAT=responses so GitHub GPT-4 and gpt-5-mini models continue to use chat completions while Codex-flavored models still route to responses.
Reset OPENAI_API_FORMAT in the affected API provider tests to prevent environment leakage across serial Bun test runs.
Verified with: bun test --max-concurrency=1
* fix: restore provider-specific model routing
Resolve generic OpenAI-compatible profiles by their known descriptor base URLs so saved MiniMax, xAI, NVIDIA NIM, OpenRouter, and DeepSeek profiles use the correct route catalogs instead of the generic OpenAI model list.
Fix MiniMax defaults and display handling so provider-specific model IDs are not rendered as Claude Opus defaults, add current MiniMax M2.7 options, and cover the regressions with focused route/model tests.
Also clean up descriptor follow-ups from review: remove the dead OpenAI shim store-strip fallback list, preserve gateway vendor IDs for Bedrock/Vertex/GitHub profile resolution, and keep the ModelPicker compiled-form changes in this PR.
* test: cover provider precedence review fixes
Remove import-time ANTHROPIC_BASE_URL and ANTHROPIC_MODEL reads from the Anthropic descriptor so descriptor defaults stay static and live env handling remains in preset metadata.
Add getAPIProvider precedence coverage documenting that explicit Gemini/OpenAI flags beat env-only MiniMax API key inference.
Add a regression check to keep the removed openaiShim hardcoded descriptor route fallback list from returning.
---------
Co-authored-by: TechBrewBoss <dash@hicap.ai>
|
||
 viudesandGitHub
|
9e23c2bec4 |
feat(api): expose cache metrics in REPL + normalize across providers (#813)
* feat(api): expose cache metrics in REPL + /cache-stats command * fix(api): normalize Kimi/DeepSeek/Gemini cache fields through shim layer * test(api): cover /cache-stats rendering + fix CacheMetrics docstring drift * fix(api): always reset cache turn counter + include date in /cache-stats rows * refactor(api): unify shim usage builder + add cost-tracker wiring test * fix(api): classify private-IP/self-hosted OpenAI endpoints as N/A instead of cold * fix(api): require colon guard on IPv6 ULA prefix to avoid public-host over-match * perf(api): ring buffer for cache history + hit rate clamp + .localhost TLD * fix(api): null guards on formatters + document Codex Responses API shape * fix(api): defensive start-of-turn reset + config gate fallback + env var docs * fix(api): trust forwarded cache data on self-hosted URLs (data-driven) * refactor(api): delegate streaming Responses usage to shared makeUsage helper |
||
|
JATMNandGitHub
|
ff2a380723 |
Add DeepSeek V4 flash/pro support and DeepSeek thinking compatibility (#877)
* Add DeepSeek V4 support and thinking compatibility * Fix DeepSeek profile persistence regression * Align multi-model handling with openai-multi-model |
||
 Rubens OliveiraandGitHub
|
d32a2a1329 |
docs: add Ollama launch integration documentation (#716)
Document the new `ollama launch openclaude` command as a shortcut for running OpenClaude through a local Ollama instance. This is now supported in Ollama's launch system and handles all environment variable setup automatically — no manual env vars needed. Changes: - README.md: Add "Using Ollama's launch command" section after the manual Ollama env var setup, and update the provider table to list `ollama launch` as a setup path for Ollama - docs/advanced-setup.md: Add `ollama launch` as the recommended method at the top of the Ollama section, with the manual env var approach kept below as an alternative |
||
 Henrique FernandesandGitHub
|
fc7dc9ca0d |
Add Codex OAuth provider flow for ChatGPT account sign-in (#503)
* feat: add Codex OAuth provider flow * fix: harden Codex OAuth storage, session activation, and UI |
||
 lunamonkeandGitHub
|
4c50977f3c |
Decouple and fix mistral (#595)
* decouple and fix mistral * fix wrong variable for currentBaseUrl and buildAPIProviderProperties |